# What can I run locally? (slim)

> Which open-weight model to run on your own machine for the job you pick, with the build that fits, an estimate of its speed and what it costs in electricity, with your hardware and power price guessed for you.

- Full: https://www.anchorterminal.com/open-weights/calculator/index.md (~8,900 tokens) · this version ~8,830 tokens · JSON https://www.anchorterminal.com/open-weights/calculator/index.json · canonical https://www.anchorterminal.com/open-weights/calculator/
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-09
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Which open-weight model to run on your own machine, for the job you pick, and what it costs in power. We guess your hardware from what your browser says and your electricity price from your time zone, and you can change both. 120 graded models, each with the builds that fit.

The page runs the sum in the browser. This twin carries the same data and the method, so an agent can do it directly. The whole data set is in the page's JSON twin (https://www.anchorterminal.com/open-weights/calculator/index.json).

## How it works

- A model fits when the build's memory need, the file plus a fifth for the runtime and a working context, is no more than your memory times the share a model can have (92% of a graphics card, two thirds to three quarters of unified memory, 60% of a computer's RAM).
- The pick is the best-graded model for the job with a build that fits and runs on your kind of machine, in its 8-bit build if that fits, then 6, 5 and 4-bit. A 16-bit build is picked only when nothing quantised fits, since it runs at about half the speed for little gain.
- Speed is an estimate for one stream, from your memory bandwidth and the gigabytes read for each token (the build's size times the share of parameters active at once). Real speed depends on the runtime, the context length and the settings.
- Cost is power under load times hours a day, at your electricity price, and per million tokens at the estimated speed. It leaves out the machine itself.

Nothing a browser reports is sent to us.

## The machines it knows

Memory and bandwidth are the makers' published figures. Power is a graphics card's board power, or our estimate for a whole machine under load (est.).

| Machine | Memory | Usable share | Bandwidth | Power |
| --- | --- | --- | --- | --- |
| NVIDIA RTX 3060 12 GB | 12 GB | 92% | 360 GB/s | 170 W |
| NVIDIA RTX 4060 Ti 16 GB | 16 GB | 92% | 288 GB/s | 165 W |
| NVIDIA RTX 3090 24 GB | 24 GB | 92% | 936 GB/s | 350 W |
| NVIDIA RTX 4090 24 GB | 24 GB | 92% | 1008 GB/s | 450 W |
| NVIDIA RTX 5070 Ti 16 GB | 16 GB | 92% | 896 GB/s | 300 W |
| NVIDIA RTX 5080 16 GB | 16 GB | 92% | 960 GB/s | 360 W |
| NVIDIA RTX 5090 32 GB | 32 GB | 92% | 1792 GB/s | 575 W |
| NVIDIA RTX PRO 6000 Blackwell 96 GB | 96 GB | 92% | 1792 GB/s | 600 W |
| Apple M1, M2 or M3 | 8, 16, 24 GB | 67% | 100 GB/s | 30 W est. |
| Apple M1 Pro, M2 Pro or M3 Pro | 16, 18, 32, 36 GB | 67% | 150 GB/s | 50 W est. |
| Apple M1 Max, M2 Max or M3 Max | 32, 36, 48, 64, 96, 128 GB | 75% | 400 GB/s | 80 W est. |
| Apple M1 Ultra or M2 Ultra | 64, 128, 192 GB | 75% | 800 GB/s | 160 W est. |
| Apple M4 | 16, 24, 32 GB | 67% | 120 GB/s | 30 W est. |
| Apple M4 Pro | 24, 48, 64 GB | 67% | 273 GB/s | 60 W est. |
| Apple M4 Max | 36, 48, 64, 128 GB | 75% | 546 GB/s | 90 W est. |
| Apple M3 Ultra | 96, 256, 512 GB | 75% | 819 GB/s | 180 W est. |
| Apple M5 | 16, 24, 32 GB | 67% | 153 GB/s | 30 W est. |
| Apple M5 Pro | 24, 48, 64 GB | 67% | 307 GB/s | 65 W est. |
| Apple M5 Max | 36, 48, 64, 128 GB | 75% | 614 GB/s | 100 W est. |
| AMD Ryzen AI Max+ 395 (Strix Halo) | 64, 96, 128 GB | 75% | 256 GB/s | 140 W est. |
| NVIDIA DGX Spark | 128 GB | 85% | 273 GB/s | 200 W est. |
| Any computer, on the CPU | 8, 16, 32, 64, 128 GB | 60% | 80 GB/s | 100 W est. |

## Electricity prices

Household prices in US dollars a kWh, GlobalPetrolPrices' 2023 to 2026 averages (https://www.globalpetrolprices.com/electricity_prices/), read on 9 November 2026. World average (Q3 2026): $0.179.

| Country | $ a kWh |
| --- | --- |
| Argentina | 0.092 |
| Australia | 0.259 |
| Austria | 0.356 |
| Belgium | 0.409 |
| Brazil | 0.166 |
| Canada | 0.123 |
| China | 0.076 |
| Czechia | 0.350 |
| Denmark | 0.352 |
| Finland | 0.177 |
| France | 0.276 |
| Germany | 0.409 |
| Hong Kong | 0.184 |
| India | 0.076 |
| Indonesia | 0.090 |
| Ireland | 0.453 |
| Israel | 0.188 |
| Italy | 0.415 |
| Japan | 0.227 |
| Mexico | 0.110 |
| Netherlands | 0.287 |
| New Zealand | 0.213 |
| Nigeria | 0.036 |
| Norway | 0.169 |
| Philippines | 0.211 |
| Poland | 0.236 |
| Portugal | 0.240 |
| Romania | 0.233 |
| Singapore | 0.236 |
| South Africa | 0.215 |
| South Korea | 0.126 |
| Spain | 0.259 |
| Sweden | 0.247 |
| Switzerland | 0.367 |
| Taiwan | 0.099 |
| Türkiye | 0.067 |
| Ukraine | 0.085 |
| United Arab Emirates | 0.080 |
| United Kingdom | 0.405 |
| United States | 0.190 |
| Vietnam | 0.078 |

## Models by job

Best grade first, with the smallest memory any build needs. Each model's builds, with their memory needs, are on its listing and in this page's JSON twin.

### Agents and tool calling

| Model | Grade | Parameters | Smallest build needs |
| --- | --- | --- | --- |
| [Gemma 4 31B IT](https://www.anchorterminal.com/tools/gemma-4-31b-it.md) | BB 74.1 | 30.7B | 24 GB |
| [Gemma 4 12B IT](https://www.anchorterminal.com/tools/gemma-4-12b-it.md) | BB 72.3 | 11.95B | 12 GB |
| [Gemma 4 26B A4B IT](https://www.anchorterminal.com/tools/gemma-4-26b-a4b-it.md) | BB 72.2 | 25.2B | 24 GB |
| [gpt-oss-120b](https://www.anchorterminal.com/tools/gpt-oss-120b.md) | BB 70.2 | 116.83B | 96 GB |
| [Muse Glimmer 30B](https://www.anchorterminal.com/tools/muse-glimmer-30b.md) | BB 70 | 29.6B | 24 GB |
| [gpt-oss-20b](https://www.anchorterminal.com/tools/gpt-oss-20b.md) | B 69.9 | 20.91B | 24 GB |
| [Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b.md) | B 69.3 | 550B | 512 GB |
| [Qwen3.8-27B](https://www.anchorterminal.com/tools/qwen3-8-27b.md) | B 68.6 | 27B | 24 GB |
| [Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/tools/nemotron-3-nano-30b-a3b.md) | B 67.6 | 30B | 24 GB |
| [Inkling-Small](https://www.anchorterminal.com/tools/inkling-small.md) | B 67 | 276B | 256 GB |
| [Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/tools/nemotron-3-super-120b-a12b.md) | B 66.7 | 120B | 128 GB |
| [Qwen3.6-27B](https://www.anchorterminal.com/tools/qwen3-6-27b.md) | B 66.7 | 27B | 24 GB |
| [GLM-5.3-Flash](https://www.anchorterminal.com/tools/glm-5-3-flash.md) | B 65.1 | 320B | 256 GB |
| [Inkling](https://www.anchorterminal.com/tools/inkling.md) | B 64.7 | 975B | 1024 GB |
| [Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/tools/nemotron-3-5-lightning-30b-a3b.md) | B 64.7 | 30B | 24 GB |
| [GLM-5.3](https://www.anchorterminal.com/tools/glm-5-3.md) | B 64.6 | 744B | 1024 GB |
| [Qwen3.5-397B-A17B](https://www.anchorterminal.com/tools/qwen3-5-397b-a17b.md) | B 64.1 | 397B total, 17B active | 512 GB |
| [Gemma 4 E4B IT](https://www.anchorterminal.com/tools/gemma-4-e4b-it.md) | B 63.2 | 8B | 8 GB |
| [Qwen3.5-122B-A10B](https://www.anchorterminal.com/tools/qwen3-5-122b-a10b.md) | B 63.1 | 122B total, 10B active | 96 GB |
| [GLM-4.7-Flash](https://www.anchorterminal.com/tools/glm-4-7-flash.md) | B 63 | 30B | 24 GB |
| [Qwen3.6-35B-A3B](https://www.anchorterminal.com/tools/qwen3-6-35b-a3b.md) | B 62.7 | 35B | 32 GB |
| [Hy3](https://www.anchorterminal.com/tools/hy3.md) | B 62.6 | 295B | 128 GB |
| [Kimi K3](https://www.anchorterminal.com/tools/kimi-k3.md) | B 62.4 | 2.8T | 2048 GB |
| [DeepSeek-V4-Flash-0731](https://www.anchorterminal.com/tools/deepseek-v4-flash-0731.md) | C 61.9 | 284B | 256 GB |
| [Qwen3.8-Flash-Next](https://www.anchorterminal.com/tools/qwen3-8-flash-next.md) | C 61.8 | 125B | 128 GB |
| [DeepSeek V4.1 Flash](https://www.anchorterminal.com/tools/deepseek-v4-1-flash.md) | C 61.5 | 552B | 1024 GB |
| [Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/tools/nemotron-3-nano-omni-30b-a3b-reasoning.md) | C 61.2 | 31B | 32 GB |
| [Qwen3.5-4B](https://www.anchorterminal.com/tools/qwen3-5-4b.md) | C 61.2 | 4B | 8 GB |
| [Agents-A1-4B](https://www.anchorterminal.com/tools/agents-a1-4b.md) | C 61 | 4.5B | 8 GB |
| [Apertus v1.5 8B](https://www.anchorterminal.com/tools/apertus-v1-5-8b.md) | C 61 | 8.9B | 24 GB |
| [Apodex-1.1-mini](https://www.anchorterminal.com/tools/apodex-1-1-mini.md) | C 61 | 35B (3B active) | 32 GB |
| [Kolibri-1](https://www.anchorterminal.com/tools/kolibri-1.md) | C 61 | 78.1B | 96 GB |
| [Laguna S 2.1](https://www.anchorterminal.com/tools/laguna-s-2-1.md) | C 61 | 117.6B total, 8B active | 96 GB |
| [Laguna XS 2.1](https://www.anchorterminal.com/tools/laguna-xs-2-1.md) | C 61 | 33.4B total, 3B active | 32 GB |
| [MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/tools/mimo-v2-6-distill-qwen-9b.md) | C 61 | 9.41B | 8 GB |
| [NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb.md) | C 61 | 8B | 8 GB |
| [Ornith-1.5-35B-A3B](https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b.md) | C 61 | 35B (3B active) | 24 GB |
| [Ornith-1.5-9B](https://www.anchorterminal.com/tools/ornith-1-5-9b.md) | C 61 | 9B | 8 GB |
| [Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-2b-instruct.md) | C 61 | 2.13B | 8 GB |
| [Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/tools/qwopus3-8-27b-flash-v2.md) | C 61 | 27.8B | 24 GB |
| [Recursive Flint](https://www.anchorterminal.com/tools/recursive-flint.md) | C 61 | 39.8B total, about 2.5B active | 32 GB |
| [SmolLM3-3B](https://www.anchorterminal.com/tools/smollm3-3b.md) | C 61 | 3.08B | 8 GB |
| [Spark-X2.6-4B](https://www.anchorterminal.com/tools/spark-x2-6-4b.md) | C 61 | 4.11B | 8 GB |
| [Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-27b.md) | C 61 | 27B | 24 GB |
| [ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/tools/thinkingcap-qwen3-8-27b.md) | C 61 | 27B | 24 GB |
| [occamy-1.0](https://www.anchorterminal.com/tools/occamy-1-0.md) | C 61 | 35B (3B active) | 24 GB |
| [Nanbeige4.3-33B](https://www.anchorterminal.com/tools/nanbeige-4-3-33b.md) | C 60.8 | 33B | 32 GB |
| [Qwen3.5-9B](https://www.anchorterminal.com/tools/qwen3-5-9b.md) | C 60.5 | 9B | 8 GB |
| [Gemma 4 E2B IT](https://www.anchorterminal.com/tools/gemma-4-e2b-it.md) | C 60.4 | 5.1B | 8 GB |
| [GLM-4.5-Air](https://www.anchorterminal.com/tools/glm-4-5-air.md) | C 60.3 | 106B | 192 GB |
| [Granite 4.2 3B](https://www.anchorterminal.com/tools/granite-4-2-3b.md) | C 59.8 | 3.66B | 8 GB |
| [MiniCPM5-2B](https://www.anchorterminal.com/tools/minicpm5-2b.md) | C 59.7 | 2.5B | 8 GB |
| [MiniMax-M2.5](https://www.anchorterminal.com/tools/minimax-m2-5.md) | C 59 | 228.7B | 512 GB |
| [Ornith-1.5-397B](https://www.anchorterminal.com/tools/ornith-1-5-397b.md) | C 59 | 397B | 512 GB |
| [DeepSeek-V3.2](https://www.anchorterminal.com/tools/deepseek-v3-2.md) | C 58.6 | 685B | 1024 GB |
| [Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-30b-a3b-instruct.md) | C 58 | 31.1B (3B active) | 24 GB |
| [MiniMax-M2.7](https://www.anchorterminal.com/tools/minimax-m2-7.md) | C 57.6 | 228.7B | 192 GB |
| [Qwen3-Coder-Next](https://www.anchorterminal.com/tools/qwen3-coder-next.md) | C 57.6 | 80B total, 3B active | 64 GB |
| [Nemotron 3 Nano 4B](https://www.anchorterminal.com/tools/nemotron-3-nano-4b.md) | C 56.8 | 4B | 8 GB |
| [Laguna M.1](https://www.anchorterminal.com/tools/laguna-m-1.md) | C 56.7 | 225.8B total, 23B active | 192 GB |
| [Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/tools/qwen3-30b-a3b-instruct-2507.md) | C 56.6 | 30.5B (3.3B active) | 24 GB |
| [Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-32b-instruct.md) | C 56.4 | 33.36B | 32 GB |
| [BigBang-v1](https://www.anchorterminal.com/tools/bigbang-v1.md) | C 56.3 | 35B (3B active) | 96 GB |
| [Ling-3.0-tiny](https://www.anchorterminal.com/tools/ling-3-0-tiny.md) | C 56.2 | 7.9B (1.3B active) | 8 GB |
| [Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/tools/qwen3-coder-30b-a3b-instruct.md) | C 55.7 | 30.5B (3.3B active) | 24 GB |
| [Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-8b-instruct.md) | C 54.9 | 8.77B | 8 GB |
| [Mistral Large 4](https://www.anchorterminal.com/tools/mistral-large-4.md) | C 54.6 | ~1T total (1.05T per Mistral's docs), 52B active | 1024 GB |
| [Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/tools/qwen3-4b-instruct-2507.md) | C 54.5 | 4B | 8 GB |
| [MiniMax-M3.1-Flash](https://www.anchorterminal.com/tools/minimax-m3-1-flash.md) | C 54.3 | 428B | 512 GB |
| [Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-flash-next.md) | C 54.2 | 125B | 128 GB |
| [Ripple-65B Preview](https://www.anchorterminal.com/tools/ripple-65b-preview.md) | D 53.3 | 65B | 69 GB |
| [Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-4b-instruct.md) | D 52.6 | 4.44B | 8 GB |
| [DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/tools/diffusiongemma-26b-a4b-it.md) | D 51.3 | 25.2B | 64 GB |
| [Qwen3.5-2B](https://www.anchorterminal.com/tools/qwen3-5-2b.md) | D 50.5 | 2B | 8 GB |
| [LFM2.5-2.6B](https://www.anchorterminal.com/tools/lfm2-5-2-6b.md) | D 50.3 | 2.69B | 8 GB |
| [Qwen3.5-0.8B](https://www.anchorterminal.com/tools/qwen3-5-0-8b.md) | D 46.7 | 0.8B | 8 GB |
| [Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/tools/qwen3-omni-30b-a3b-instruct.md) | E 41.8 | 35.3B (3B active) | 96 GB |

### Chat and reasoning

| Model | Grade | Parameters | Smallest build needs |
| --- | --- | --- | --- |
| [Gemma 4 31B IT](https://www.anchorterminal.com/tools/gemma-4-31b-it.md) | BB 74.1 | 30.7B | 24 GB |
| [Gemma 4 12B IT](https://www.anchorterminal.com/tools/gemma-4-12b-it.md) | BB 72.3 | 11.95B | 12 GB |
| [Gemma 4 26B A4B IT](https://www.anchorterminal.com/tools/gemma-4-26b-a4b-it.md) | BB 72.2 | 25.2B | 24 GB |
| [gpt-oss-120b](https://www.anchorterminal.com/tools/gpt-oss-120b.md) | BB 70.2 | 116.83B | 96 GB |
| [Muse Glimmer 30B](https://www.anchorterminal.com/tools/muse-glimmer-30b.md) | BB 70 | 29.6B | 24 GB |
| [gpt-oss-20b](https://www.anchorterminal.com/tools/gpt-oss-20b.md) | B 69.9 | 20.91B | 24 GB |
| [Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b.md) | B 69.3 | 550B | 512 GB |
| [Qwen3.8-27B](https://www.anchorterminal.com/tools/qwen3-8-27b.md) | B 68.6 | 27B | 24 GB |
| [Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/tools/nemotron-3-nano-30b-a3b.md) | B 67.6 | 30B | 24 GB |
| [Inkling-Small](https://www.anchorterminal.com/tools/inkling-small.md) | B 67 | 276B | 256 GB |
| [Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/tools/nemotron-3-super-120b-a12b.md) | B 66.7 | 120B | 128 GB |
| [Qwen3.6-27B](https://www.anchorterminal.com/tools/qwen3-6-27b.md) | B 66.7 | 27B | 24 GB |
| [GLM-5.3-Flash](https://www.anchorterminal.com/tools/glm-5-3-flash.md) | B 65.1 | 320B | 256 GB |
| [Inkling](https://www.anchorterminal.com/tools/inkling.md) | B 64.7 | 975B | 1024 GB |
| [Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/tools/nemotron-3-5-lightning-30b-a3b.md) | B 64.7 | 30B | 24 GB |
| [GLM-5.3](https://www.anchorterminal.com/tools/glm-5-3.md) | B 64.6 | 744B | 1024 GB |
| [Qwen3.5-397B-A17B](https://www.anchorterminal.com/tools/qwen3-5-397b-a17b.md) | B 64.1 | 397B total, 17B active | 512 GB |
| [Gemma 4 E4B IT](https://www.anchorterminal.com/tools/gemma-4-e4b-it.md) | B 63.2 | 8B | 8 GB |
| [Qwen3.5-122B-A10B](https://www.anchorterminal.com/tools/qwen3-5-122b-a10b.md) | B 63.1 | 122B total, 10B active | 96 GB |
| [GLM-4.7-Flash](https://www.anchorterminal.com/tools/glm-4-7-flash.md) | B 63 | 30B | 24 GB |
| [Qwen3.6-35B-A3B](https://www.anchorterminal.com/tools/qwen3-6-35b-a3b.md) | B 62.7 | 35B | 32 GB |
| [Hy3](https://www.anchorterminal.com/tools/hy3.md) | B 62.6 | 295B | 128 GB |
| [Kimi K3](https://www.anchorterminal.com/tools/kimi-k3.md) | B 62.4 | 2.8T | 2048 GB |
| [DeepSeek-V4-Flash-0731](https://www.anchorterminal.com/tools/deepseek-v4-flash-0731.md) | C 61.9 | 284B | 256 GB |
| [Qwen3.8-Flash-Next](https://www.anchorterminal.com/tools/qwen3-8-flash-next.md) | C 61.8 | 125B | 128 GB |
| [DeepSeek V4.1 Flash](https://www.anchorterminal.com/tools/deepseek-v4-1-flash.md) | C 61.5 | 552B | 1024 GB |
| [Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/tools/nemotron-3-nano-omni-30b-a3b-reasoning.md) | C 61.2 | 31B | 32 GB |
| [Qwen3.5-4B](https://www.anchorterminal.com/tools/qwen3-5-4b.md) | C 61.2 | 4B | 8 GB |
| [Agents-A1-4B](https://www.anchorterminal.com/tools/agents-a1-4b.md) | C 61 | 4.5B | 8 GB |
| [Apertus v1.5 8B](https://www.anchorterminal.com/tools/apertus-v1-5-8b.md) | C 61 | 8.9B | 24 GB |
| [Apodex-1.1-mini](https://www.anchorterminal.com/tools/apodex-1-1-mini.md) | C 61 | 35B (3B active) | 32 GB |
| [Carbon-X](https://www.anchorterminal.com/tools/carbon-x.md) | C 61 | 14.8B | 12 GB |
| [Darwin-36B-Opus](https://www.anchorterminal.com/tools/darwin-36b-opus.md) | C 61 | 35B (3B active) | 12 GB |
| [Kolibri-1](https://www.anchorterminal.com/tools/kolibri-1.md) | C 61 | 78.1B | 96 GB |
| [Laguna S 2.1](https://www.anchorterminal.com/tools/laguna-s-2-1.md) | C 61 | 117.6B total, 8B active | 96 GB |
| [Laguna XS 2.1](https://www.anchorterminal.com/tools/laguna-xs-2-1.md) | C 61 | 33.4B total, 3B active | 32 GB |
| [MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/tools/mimo-v2-6-distill-qwen-9b.md) | C 61 | 9.41B | 8 GB |
| [MiniCPM-o 4.5](https://www.anchorterminal.com/tools/minicpm-o-4-5.md) | C 61 | 9.4B | 8 GB |
| [NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb.md) | C 61 | 8B | 8 GB |
| [Ornith-1.5-35B-A3B](https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b.md) | C 61 | 35B (3B active) | 24 GB |
| [Ornith-1.5-9B](https://www.anchorterminal.com/tools/ornith-1-5-9b.md) | C 61 | 9B | 8 GB |
| [Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-2b-instruct.md) | C 61 | 2.13B | 8 GB |
| [Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/tools/qwopus3-8-27b-flash-v2.md) | C 61 | 27.8B | 24 GB |
| [Recursive Flint](https://www.anchorterminal.com/tools/recursive-flint.md) | C 61 | 39.8B total, about 2.5B active | 32 GB |
| [SmolLM3-3B](https://www.anchorterminal.com/tools/smollm3-3b.md) | C 61 | 3.08B | 8 GB |
| [Spark-X2.6-4B](https://www.anchorterminal.com/tools/spark-x2-6-4b.md) | C 61 | 4.11B | 8 GB |
| [Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-27b.md) | C 61 | 27B | 24 GB |
| [ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/tools/thinkingcap-qwen3-8-27b.md) | C 61 | 27B | 24 GB |
| [occamy-1.0](https://www.anchorterminal.com/tools/occamy-1-0.md) | C 61 | 35B (3B active) | 24 GB |
| [Nanbeige4.3-33B](https://www.anchorterminal.com/tools/nanbeige-4-3-33b.md) | C 60.8 | 33B | 32 GB |
| [Qwen3.5-9B](https://www.anchorterminal.com/tools/qwen3-5-9b.md) | C 60.5 | 9B | 8 GB |
| [Gemma 4 E2B IT](https://www.anchorterminal.com/tools/gemma-4-e2b-it.md) | C 60.4 | 5.1B | 8 GB |
| [GLM-4.5-Air](https://www.anchorterminal.com/tools/glm-4-5-air.md) | C 60.3 | 106B | 192 GB |
| [Granite 4.2 3B](https://www.anchorterminal.com/tools/granite-4-2-3b.md) | C 59.8 | 3.66B | 8 GB |
| [MiniCPM5-2B](https://www.anchorterminal.com/tools/minicpm5-2b.md) | C 59.7 | 2.5B | 8 GB |
| [Cosmos-Reason2-2B](https://www.anchorterminal.com/tools/cosmos-reason2-2b.md) | C 59.5 | 2.44B | 8 GB |
| [MiniMax-M2.5](https://www.anchorterminal.com/tools/minimax-m2-5.md) | C 59 | 228.7B | 512 GB |
| [Ornith-1.5-397B](https://www.anchorterminal.com/tools/ornith-1-5-397b.md) | C 59 | 397B | 512 GB |
| [DeepSeek-V3.2](https://www.anchorterminal.com/tools/deepseek-v3-2.md) | C 58.6 | 685B | 1024 GB |
| [Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-30b-a3b-instruct.md) | C 58 | 31.1B (3B active) | 24 GB |
| [MiniMax-M2.7](https://www.anchorterminal.com/tools/minimax-m2-7.md) | C 57.6 | 228.7B | 192 GB |
| [Qwen3-Coder-Next](https://www.anchorterminal.com/tools/qwen3-coder-next.md) | C 57.6 | 80B total, 3B active | 64 GB |
| [Nemotron 3 Nano 4B](https://www.anchorterminal.com/tools/nemotron-3-nano-4b.md) | C 56.8 | 4B | 8 GB |
| [Laguna M.1](https://www.anchorterminal.com/tools/laguna-m-1.md) | C 56.7 | 225.8B total, 23B active | 192 GB |
| [Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/tools/qwen3-30b-a3b-instruct-2507.md) | C 56.6 | 30.5B (3.3B active) | 24 GB |
| [Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-32b-instruct.md) | C 56.4 | 33.36B | 32 GB |
| [BigBang-v1](https://www.anchorterminal.com/tools/bigbang-v1.md) | C 56.3 | 35B (3B active) | 96 GB |
| [Ling-3.0-tiny](https://www.anchorterminal.com/tools/ling-3-0-tiny.md) | C 56.2 | 7.9B (1.3B active) | 8 GB |
| [LBS-27B](https://www.anchorterminal.com/tools/lbs-27b.md) | C 55.8 | 27B | 96 GB |
| [Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/tools/qwen3-coder-30b-a3b-instruct.md) | C 55.7 | 30.5B (3.3B active) | 24 GB |
| [Kronos](https://www.anchorterminal.com/tools/kronos.md) | C 55.2 | 4.1M to 102.3M | 8 GB |
| [Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-8b-instruct.md) | C 54.9 | 8.77B | 8 GB |
| [Mistral Large 4](https://www.anchorterminal.com/tools/mistral-large-4.md) | C 54.6 | ~1T total (1.05T per Mistral's docs), 52B active | 1024 GB |
| [Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/tools/qwen3-4b-instruct-2507.md) | C 54.5 | 4B | 8 GB |
| [MiniMax-M3.1-Flash](https://www.anchorterminal.com/tools/minimax-m3-1-flash.md) | C 54.3 | 428B | 512 GB |
| [Baidu Unlimited-OCR-2](https://www.anchorterminal.com/tools/unlimited-ocr-2.md) | C 54.2 | 3.3B (3B-A0.5B mixture-of-experts decoder per the report) | 12 GB |
| [Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-flash-next.md) | C 54.2 | 125B | 128 GB |
| [Ripple-65B Preview](https://www.anchorterminal.com/tools/ripple-65b-preview.md) | D 53.3 | 65B | 69 GB |
| [InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/tools/internvl3-5-gpt-oss-20b-a4b-preview.md) | D 53.2 | 21.2B | 64 GB |
| [Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-4b-instruct.md) | D 52.6 | 4.44B | 8 GB |
| [Olmo 3 7B Think](https://www.anchorterminal.com/tools/olmo-3-7b-think.md) | D 52.3 | 7.3B | 8 GB |
| [DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/tools/diffusiongemma-26b-a4b-it.md) | D 51.3 | 25.2B | 64 GB |
| [Qwen3.5-2B](https://www.anchorterminal.com/tools/qwen3-5-2b.md) | D 50.5 | 2B | 8 GB |
| [LFM2.5-2.6B](https://www.anchorterminal.com/tools/lfm2-5-2-6b.md) | D 50.3 | 2.69B | 8 GB |
| [Qwen3.5-0.8B](https://www.anchorterminal.com/tools/qwen3-5-0-8b.md) | D 46.7 | 0.8B | 8 GB |
| [Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/tools/qwen3-omni-30b-a3b-instruct.md) | E 41.8 | 35.3B (3B active) | 96 GB |

### Coding

| Model | Grade | Parameters | Smallest build needs |
| --- | --- | --- | --- |
| [Qwen3.6-27B](https://www.anchorterminal.com/tools/qwen3-6-27b.md) | B 66.7 | 27B | 24 GB |
| [GLM-5.3](https://www.anchorterminal.com/tools/glm-5-3.md) | B 64.6 | 744B | 1024 GB |
| [Laguna S 2.1](https://www.anchorterminal.com/tools/laguna-s-2-1.md) | C 61 | 117.6B total, 8B active | 96 GB |
| [Laguna XS 2.1](https://www.anchorterminal.com/tools/laguna-xs-2-1.md) | C 61 | 33.4B total, 3B active | 32 GB |
| [Ornith-1.5-35B-A3B](https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b.md) | C 61 | 35B (3B active) | 24 GB |
| [Ornith-1.5-9B](https://www.anchorterminal.com/tools/ornith-1-5-9b.md) | C 61 | 9B | 8 GB |
| [Recursive Flint](https://www.anchorterminal.com/tools/recursive-flint.md) | C 61 | 39.8B total, about 2.5B active | 32 GB |
| [occamy-1.0](https://www.anchorterminal.com/tools/occamy-1-0.md) | C 61 | 35B (3B active) | 24 GB |
| [Nanbeige4.3-33B](https://www.anchorterminal.com/tools/nanbeige-4-3-33b.md) | C 60.8 | 33B | 32 GB |
| [MiniMax-M2.5](https://www.anchorterminal.com/tools/minimax-m2-5.md) | C 59 | 228.7B | 512 GB |
| [Ornith-1.5-397B](https://www.anchorterminal.com/tools/ornith-1-5-397b.md) | C 59 | 397B | 512 GB |
| [MiniMax-M2.7](https://www.anchorterminal.com/tools/minimax-m2-7.md) | C 57.6 | 228.7B | 192 GB |
| [Qwen3-Coder-Next](https://www.anchorterminal.com/tools/qwen3-coder-next.md) | C 57.6 | 80B total, 3B active | 64 GB |
| [Laguna M.1](https://www.anchorterminal.com/tools/laguna-m-1.md) | C 56.7 | 225.8B total, 23B active | 192 GB |
| [Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/tools/qwen3-coder-30b-a3b-instruct.md) | C 55.7 | 30.5B (3.3B active) | 24 GB |
| [MiniMax-M3.1-Flash](https://www.anchorterminal.com/tools/minimax-m3-1-flash.md) | C 54.3 | 428B | 512 GB |
| [Ripple-65B Preview](https://www.anchorterminal.com/tools/ripple-65b-preview.md) | D 53.3 | 65B | 69 GB |

### Images and video in

| Model | Grade | Parameters | Smallest build needs |
| --- | --- | --- | --- |
| [Gemma 4 31B IT](https://www.anchorterminal.com/tools/gemma-4-31b-it.md) | BB 74.1 | 30.7B | 24 GB |
| [Gemma 4 12B IT](https://www.anchorterminal.com/tools/gemma-4-12b-it.md) | BB 72.3 | 11.95B | 12 GB |
| [Gemma 4 26B A4B IT](https://www.anchorterminal.com/tools/gemma-4-26b-a4b-it.md) | BB 72.2 | 25.2B | 24 GB |
| [Muse Glimmer 30B](https://www.anchorterminal.com/tools/muse-glimmer-30b.md) | BB 70 | 29.6B | 24 GB |
| [Qwen3.8-27B](https://www.anchorterminal.com/tools/qwen3-8-27b.md) | B 68.6 | 27B | 24 GB |
| [Inkling-Small](https://www.anchorterminal.com/tools/inkling-small.md) | B 67 | 276B | 256 GB |
| [Qwen3.6-27B](https://www.anchorterminal.com/tools/qwen3-6-27b.md) | B 66.7 | 27B | 24 GB |
| [GLM-5.3-Flash](https://www.anchorterminal.com/tools/glm-5-3-flash.md) | B 65.1 | 320B | 256 GB |
| [Inkling](https://www.anchorterminal.com/tools/inkling.md) | B 64.7 | 975B | 1024 GB |
| [Qwen3.5-397B-A17B](https://www.anchorterminal.com/tools/qwen3-5-397b-a17b.md) | B 64.1 | 397B total, 17B active | 512 GB |
| [Gemma 4 E4B IT](https://www.anchorterminal.com/tools/gemma-4-e4b-it.md) | B 63.2 | 8B | 8 GB |
| [Qwen3.5-122B-A10B](https://www.anchorterminal.com/tools/qwen3-5-122b-a10b.md) | B 63.1 | 122B total, 10B active | 96 GB |
| [Qwen3.6-35B-A3B](https://www.anchorterminal.com/tools/qwen3-6-35b-a3b.md) | B 62.7 | 35B | 32 GB |
| [Kimi K3](https://www.anchorterminal.com/tools/kimi-k3.md) | B 62.4 | 2.8T | 2048 GB |
| [Qwen3.8-Flash-Next](https://www.anchorterminal.com/tools/qwen3-8-flash-next.md) | C 61.8 | 125B | 128 GB |
| [DeepSeek V4.1 Flash](https://www.anchorterminal.com/tools/deepseek-v4-1-flash.md) | C 61.5 | 552B | 1024 GB |
| [Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/tools/nemotron-3-nano-omni-30b-a3b-reasoning.md) | C 61.2 | 31B | 32 GB |
| [Qwen3.5-4B](https://www.anchorterminal.com/tools/qwen3-5-4b.md) | C 61.2 | 4B | 8 GB |
| [Agents-A1-4B](https://www.anchorterminal.com/tools/agents-a1-4b.md) | C 61 | 4.5B | 8 GB |
| [Apertus v1.5 8B](https://www.anchorterminal.com/tools/apertus-v1-5-8b.md) | C 61 | 8.9B | 24 GB |
| [Apodex-1.1-mini](https://www.anchorterminal.com/tools/apodex-1-1-mini.md) | C 61 | 35B (3B active) | 32 GB |
| [MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/tools/mimo-v2-6-distill-qwen-9b.md) | C 61 | 9.41B | 8 GB |
| [MiniCPM-o 4.5](https://www.anchorterminal.com/tools/minicpm-o-4-5.md) | C 61 | 9.4B | 8 GB |
| [Ornith-1.5-35B-A3B](https://www.anchorterminal.com/tools/ornith-1-5-35b-a3b.md) | C 61 | 35B (3B active) | 24 GB |
| [Ornith-1.5-9B](https://www.anchorterminal.com/tools/ornith-1-5-9b.md) | C 61 | 9B | 8 GB |
| [Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-2b-instruct.md) | C 61 | 2.13B | 8 GB |
| [Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/tools/qwopus3-8-27b-flash-v2.md) | C 61 | 27.8B | 24 GB |
| [Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-27b.md) | C 61 | 27B | 24 GB |
| [ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/tools/thinkingcap-qwen3-8-27b.md) | C 61 | 27B | 24 GB |
| [occamy-1.0](https://www.anchorterminal.com/tools/occamy-1-0.md) | C 61 | 35B (3B active) | 24 GB |
| [Qwen3.5-9B](https://www.anchorterminal.com/tools/qwen3-5-9b.md) | C 60.5 | 9B | 8 GB |
| [Gemma 4 E2B IT](https://www.anchorterminal.com/tools/gemma-4-e2b-it.md) | C 60.4 | 5.1B | 8 GB |
| [Cosmos-Reason2-2B](https://www.anchorterminal.com/tools/cosmos-reason2-2b.md) | C 59.5 | 2.44B | 8 GB |
| [Ornith-1.5-397B](https://www.anchorterminal.com/tools/ornith-1-5-397b.md) | C 59 | 397B | 512 GB |
| [Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-30b-a3b-instruct.md) | C 58 | 31.1B (3B active) | 24 GB |
| [Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-32b-instruct.md) | C 56.4 | 33.36B | 32 GB |
| [BigBang-v1](https://www.anchorterminal.com/tools/bigbang-v1.md) | C 56.3 | 35B (3B active) | 96 GB |
| [LBS-27B](https://www.anchorterminal.com/tools/lbs-27b.md) | C 55.8 | 27B | 96 GB |
| [Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-8b-instruct.md) | C 54.9 | 8.77B | 8 GB |
| [Mistral Large 4](https://www.anchorterminal.com/tools/mistral-large-4.md) | C 54.6 | ~1T total (1.05T per Mistral's docs), 52B active | 1024 GB |
| [MiniMax-M3.1-Flash](https://www.anchorterminal.com/tools/minimax-m3-1-flash.md) | C 54.3 | 428B | 512 GB |
| [Baidu Unlimited-OCR-2](https://www.anchorterminal.com/tools/unlimited-ocr-2.md) | C 54.2 | 3.3B (3B-A0.5B mixture-of-experts decoder per the report) | 12 GB |
| [Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/tools/swift-1-5-qwen3-8-flash-next.md) | C 54.2 | 125B | 128 GB |
| [InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/tools/internvl3-5-gpt-oss-20b-a4b-preview.md) | D 53.2 | 21.2B | 64 GB |
| [Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/tools/qwen3-vl-4b-instruct.md) | D 52.6 | 4.44B | 8 GB |
| [DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/tools/diffusiongemma-26b-a4b-it.md) | D 51.3 | 25.2B | 64 GB |
| [Qwen3.5-2B](https://www.anchorterminal.com/tools/qwen3-5-2b.md) | D 50.5 | 2B | 8 GB |
| [Qwen3.5-0.8B](https://www.anchorterminal.com/tools/qwen3-5-0-8b.md) | D 46.7 | 0.8B | 8 GB |
| [Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/tools/qwen3-omni-30b-a3b-instruct.md) | E 41.8 | 35.3B (3B active) | 96 GB |

### Documents and OCR

| Model | Grade | Parameters | Smallest build needs |
| --- | --- | --- | --- |
| [Nemotron 3.5 Parse](https://www.anchorterminal.com/tools/nemotron-3-5-parse.md) | B 69 | 0.63B | 8 GB |
| [Xiaomi-OCR-0](https://www.anchorterminal.com/tools/xiaomi-ocr-0.md) | C 59 | 0.87B (873,438,784 by the Hub's count; 0.8B on the card) | 8 GB |
| [Baidu Unlimited-OCR-2](https://www.anchorterminal.com/tools/unlimited-ocr-2.md) | C 54.2 | 3.3B (3B-A0.5B mixture-of-experts decoder per the report) | 12 GB |

### Speech to text

| Model | Grade | Parameters | Smallest build needs |
| --- | --- | --- | --- |
| [Parakeet TDT 0.6B v3](https://www.anchorterminal.com/tools/parakeet-tdt-0-6b-v3.md) | B 66.9 | 0.6B | 8 GB |
| [Qwen3-ASR-1.7B](https://www.anchorterminal.com/tools/qwen3-asr-1-7b.md) | B 64.4 | 2.04B | 8 GB |
| [Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/tools/voxtral-mini-4b-realtime-2602.md) | B 62 | 4.43B | 8 GB |
| [Qwen3-ASR-0.6B](https://www.anchorterminal.com/tools/qwen3-asr-0-6b.md) | C 61.2 | 0.78B | 8 GB |
| [Cohere Transcribe 03-2026](https://www.anchorterminal.com/tools/cohere-transcribe-03-2026.md) | C 60.3 | 2.07B | 8 GB |
| [Nemotron 3.5 ASR Streaming 0.6B](https://www.anchorterminal.com/tools/nemotron-3-5-asr-streaming-0-6b.md) | C 60.3 | 0.64B | 8 GB |
| [Ming-3.0-asr-tiny](https://www.anchorterminal.com/tools/ming-3-0-asr-tiny.md) | C 54.8 | 8.87B | 24 GB |
| [Ming-3.0-audio-tiny](https://www.anchorterminal.com/tools/ming-3-0-audio-tiny.md) | D 52.1 | 9.3B | 32 GB |
| [Underdog Bark 3.0](https://www.anchorterminal.com/tools/underdog-bark-3.md) | D 48.2 | 0.6B | 8 GB |
| [Ming-3.0-audio-flash](https://www.anchorterminal.com/tools/ming-3-0-audio-flash.md) | E 42.5 | 126B | 512 GB |

### Text to speech

| Model | Grade | Parameters | Smallest build needs |
| --- | --- | --- | --- |
| [Ming-3.0-tts-0.5B](https://www.anchorterminal.com/tools/ming-3-0-tts-0-5b.md) | C 59.3 | 0.5B | 8 GB |
| [Qwen3-TTS 12Hz 1.7B CustomVoice](https://www.anchorterminal.com/tools/qwen3-tts-1-7b-customvoice.md) | C 59.2 | 1.92B (main checkpoint) plus the 12 Hz speech tokenizer | 8 GB |
| [VieNeu-TTS v3 Turbo](https://www.anchorterminal.com/tools/vieneu-tts-v3-turbo.md) | C 58.5 | 0.13B | 8 GB |
| [OmniVoice](https://www.anchorterminal.com/tools/omnivoice.md) | C 56.9 | 0.61B (main checkpoint) plus the Higgs Audio v2 tokenizer | 8 GB |
| [Fish Audio Drama 3](https://www.anchorterminal.com/tools/fish-audio-drama-3.md) | C 55.6 | 35.9B (35B backbone with about 3B active per token, per the card; 35,899,643,008 by the Hub's count) | 32 GB |
| [Ming-3.0-tts-tiny](https://www.anchorterminal.com/tools/ming-3-0-tts-tiny.md) | C 54.5 | 7.9B | 24 GB |
| [Fish Audio S2 Pro](https://www.anchorterminal.com/tools/fish-audio-s2-pro.md) | D 52.5 | 4.56B (slow AR 4B plus fast AR 0.4B, BF16) plus the codec | 16 GB |
| [Audio8-TTS-Realistic 0.6B](https://www.anchorterminal.com/tools/audio8-tts-realistic-0-6b.md) | D 51.5 | 0.6B (601,159,424 BF16 parameters by the Hub's count, without the bundled codec) | 8 GB |

### Embeddings and search

| Model | Grade | Parameters | Smallest build needs |
| --- | --- | --- | --- |
| [Qwen3-Embedding-8B](https://www.anchorterminal.com/tools/qwen3-embedding-8b.md) | BB 75.4 | 7.57B | 8 GB |
| [Qwen3-Embedding-4B](https://www.anchorterminal.com/tools/qwen3-embedding-4b.md) | BB 73.6 | 4.02B | 8 GB |
| [EmbeddingGemma 2](https://www.anchorterminal.com/tools/embeddinggemma-2.md) | B 66.4 | 740M | 8 GB |
| [Qwen3-Embedding-0.6B](https://www.anchorterminal.com/tools/qwen3-embedding-0-6b.md) | B 62.5 | 0.6B | 8 GB |
| [Qwen3-VL-Embedding-8B](https://www.anchorterminal.com/tools/qwen3-vl-embedding-8b.md) | B 62.1 | 8.14B | 24 GB |
| [Qwen3-VL-Embedding-2B](https://www.anchorterminal.com/tools/qwen3-vl-embedding-2b.md) | C 57.7 | 2.13B | 8 GB |
| [EmbeddingGemma 300M](https://www.anchorterminal.com/tools/embeddinggemma-300m.md) | D 48.9 | 308M | 8 GB |
| [jina-embeddings-v5-omni-small](https://www.anchorterminal.com/tools/jina-embeddings-v5-omni-small.md) | D 48.8 | 1.63B | 8 GB |
| [Granite Embedding Small English R2](https://www.anchorterminal.com/tools/granite-embedding-small-english-r2.md) | E 41.7 | 47M | 8 GB |

### Decisions with probabilities

| Model | Grade | Parameters | Smallest build needs |
| --- | --- | --- | --- |
| [JEV-27B-VL](https://www.anchorterminal.com/tools/jev-27b-vl.md) | C 59.5 | 27B | 96 GB |
| [joey-1](https://www.anchorterminal.com/tools/joey-1.md) | C 57.1 | 2B | 8 GB |
| [Drex Max v1](https://www.anchorterminal.com/tools/drex-max-v1.md) | C 55.5 | 27B | 24 GB |
| [elephant-1](https://www.anchorterminal.com/tools/elephant-1.md) | D 53.6 | 9B | 24 GB |
| [mammoth-1](https://www.anchorterminal.com/tools/mammoth-1.md) | D 48.6 | 27B | 96 GB |