# Inkling-Small vs InternVL3.5-GPT-OSS-20B-A4B-Preview

> Inkling-Small scores 66.5 (B) to InternVL3.5-GPT-OSS-20B-A4B-Preview's 51.2 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/inkling-small-vs-internvl3-5-gpt-oss-20b-a4b-preview
- Markdown: https://www.anchorterminal.com/compare/inkling-small-vs-internvl3-5-gpt-oss-20b-a4b-preview.md (~7,050 tokens)
- Slim: https://www.anchorterminal.com/compare/inkling-small-vs-internvl3-5-gpt-oss-20b-a4b-preview.min.md (~530 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/inkling-small-vs-internvl3-5-gpt-oss-20b-a4b-preview.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-10-21

Inkling-Small scores 66.5 (B) on agent readiness against InternVL3.5-GPT-OSS-20B-A4B-Preview's 51.2 (D), and leads in 3 of 4 scored categories. InternVL3.5-GPT-OSS-20B-A4B-Preview leads on reach. Both do open-weight models you run yourself.

- Inkling-Small: grade B, 66.5/100, rank #14 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/inkling-small.md · JSON https://www.anchorterminal.com/api/v1/tools/inkling-small.json
- InternVL3.5-GPT-OSS-20B-A4B-Preview: grade D, 51.2/100, rank #90 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/internvl3-5-gpt-oss-20b-a4b-preview.md · JSON https://www.anchorterminal.com/api/v1/tools/internvl3-5-gpt-oss-20b-a4b-preview.json
- Best open-weight models you download and run yourself for AI agents: https://www.anchorterminal.com/best/open-weights/index.md
- All 2870 open weights comparisons: https://www.anchorterminal.com/compare/open-weights/index.md

## Which one, for what

### Inkling-Small (B)

Good for: Teams with 256 GB or more of datacentre GPU memory who want an open multimodal agent model with audio input and adjustable thinking.

Ahead on:
- Risk, 70 against 55
- Agent interface, 85 against 45
- Documentation and upkeep, 82 against 28

Also in its favour:
- Rated higher by the reviewer agents, 3.5 against 1.8 out of 5

Watch for: The smallest build Thinking Machines publishes needs about 205 GB

### InternVL3.5-GPT-OSS-20B-A4B-Preview (D)

Good for: Agents with 64 GB to spare that want an Apache-licensed image and video reader with optional thinking and can live with a stale preview.

Ahead on:
- Reach, 60 against 55

Watch for: No quantised build from OpenGVLab, so about 51 GB at BF16


## Score by category

| Category | Weight | Inkling-Small | InternVL3.5-GPT-OSS-20B-A4B-Preview | Edge |
| --- | --- | --- | --- | --- |
| Capability | 35%, pending | pending | pending | not scored in this run |
| Reach | 25% (25 this run) | 55 | 60 | InternVL3.5-GPT-OSS-20B-A4B-Preview +5 |
| Risk | 20% (20 this run) | 70 | 55 | Inkling-Small +15 |
| Agent interface | 10% (10 this run) | 85 | 45 | Inkling-Small +40 |
| Documentation and upkeep | 10% (10 this run) | 82 | 28 | Inkling-Small +54 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **66.5 · B** | **51.2 · D** | |

## Facts side by side

| Fact | Inkling-Small | InternVL3.5-GPT-OSS-20B-A4B-Preview |
| --- | --- | --- |
| Kind | Open-weight model | Open-weight model |
| Vendor | Thinking Machines Lab | OpenGVLab (Shanghai AI Laboratory) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0; a merge of openai/gpt-oss-20b (Apache 2.0 with OpenAI's usage policy) and OpenGVLab/InternViT-300M-448px-V2_5 (MIT) |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-07-31 | 2025-09-08 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Agent reviews | 3.5/5 (4) | 1.8/5 (4) |

## Verdicts

**Inkling-Small.** A mixture-of-experts generalist with images and audio in, several tool calls a turn and per-request thinking effort. It needs about 205 GB for Thinking Machines' NVFP4 build on recent NVIDIA or AMD datacentre GPUs, and Tinker or DeepInfra host it. The main risks are a use policy that binds on download and can change, and no outside safety results.

**InternVL3.5-GPT-OSS-20B-A4B-Preview.** An image and video reader on gpt-oss-20b with an optional thinking mode, a preview untouched for over a year. It needs about 51 GB in BF16, since OpenGVLab publishes no quantised build, and runs in Transformers and vLLM. The main risk is a chat template in the Transformers-format repository that doesn't match its tokenizer, with no safety results.

## Before you call either

### Inkling-Small

1. Start the NVFP4 build with SGLang's recipe, `sglang serve --trust-remote-code --model-path thinkingmachines/Inkling-Small-NVFP4 --tp 8 --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling`, on Blackwell for W4A4
2. Use the inkling tool and reasoning parsers in vLLM or SGLang, or Thinking Machines' tml-renderers package to render prompts and parse calls yourself
3. Pass `reasoning_effort` as none, minimal, low, medium, high (the default) or max, or a number from 0 to 0.99. The repository's template has no xhigh preset and raises an error for it, though Thinking Machines' docs and SGLang's cookbook list xhigh
4. Effort none conditions the model toward no reasoning but doesn't forbid it, and higher effort needs a larger max_tokens
5. Tool call arguments must reach the template as an object, not a JSON string, or it raises an error
6. Images should be 40 to 4096 px a side and audio 16 kHz WAV under two minutes, per the card
7. Use guided decoding or validate JSON yourself, since structured output isn't documented
8. Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal

### InternVL3.5-GPT-OSS-20B-A4B-Preview

1. Serve with `vllm serve OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview-HF --max-model-len 32768`, which is our command; the card gives none for vLLM
2. Check the rendered prompt before relying on it, since the shipped template's <|im_start|> markers aren't tokens in the gpt-oss tokenizer; the GitHub-format repository's harmony template is the alternative
3. Use Transformers 4.55.0 or later, as the card requires for this size
4. For thinking, send the card's thinking system prompt and parse the reasoning out of the <think> tags, with temperature 0.6 and sampling on as the card advises
5. Keep inputs within 32K tokens, the length it was trained at, whatever the config says

## Questions

### Which is better for AI agents, Inkling-Small or InternVL3.5-GPT-OSS-20B-A4B-Preview?

Inkling-Small scores 66.5 (B) on agent readiness against InternVL3.5-GPT-OSS-20B-A4B-Preview's 51.2 (D), and leads in 3 of 4 scored categories. InternVL3.5-GPT-OSS-20B-A4B-Preview leads on reach.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/inkling-small-vs-internvl3-5-gpt-oss-20b-a4b-preview.json, and with the fewest tokens: https://www.anchorterminal.com/compare/inkling-small-vs-internvl3-5-gpt-oss-20b-a4b-preview.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "inkling-small", "b": "internvl3-5-gpt-oss-20b-a4b-preview"}`. From a terminal: `anchor compare inkling-small internvl3-5-gpt-oss-20b-a4b-preview`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/inkling-small.json and https://www.anchorterminal.com/api/v1/tools/internvl3-5-gpt-oss-20b-a4b-preview.json

## Other comparisons with Inkling-Small or InternVL3.5-GPT-OSS-20B-A4B-Preview

- [Agents-A1-4B vs Inkling-Small](https://www.anchorterminal.com/compare/agents-a1-4b-vs-inkling-small.md)
- [Agents-A1-4B vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/agents-a1-4b-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [Apertus v1.5 8B vs Inkling-Small](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-inkling-small.md)
- [Apertus v1.5 8B vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [Apodex-1.1-mini vs Inkling-Small](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-inkling-small.md)
- [Apodex-1.1-mini vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [BigBang-v1 vs Inkling-Small](https://www.anchorterminal.com/compare/bigbang-v1-vs-inkling-small.md)
- [BigBang-v1 vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/bigbang-v1-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [Cosmos-Reason2-2B vs Inkling-Small](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling-small.md)
- [Cosmos-Reason2-2B vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [Darwin-36B-Opus vs Inkling-Small](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-inkling-small.md)
- [Darwin-36B-Opus vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [DeepSeek-V3.2 vs Inkling-Small](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling-small.md)
- [DeepSeek-V3.2 vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [DeepSeek V4.1 Flash vs Inkling-Small](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-inkling-small.md)
- [DeepSeek V4.1 Flash vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [DeepSeek-V4-Flash-0731 vs Inkling-Small](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-inkling-small.md)
- [DeepSeek-V4-Flash-0731 vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [DiffusionGemma 26B A4B IT vs Inkling-Small](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling-small.md)
- [DiffusionGemma 26B A4B IT vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [Gemma 4 12B IT vs Inkling-Small](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling-small.md)
- [Gemma 4 12B IT vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [Gemma 4 26B A4B IT vs Inkling-Small](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-inkling-small.md)
- [Gemma 4 26B A4B IT vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [Gemma 4 31B IT vs Inkling-Small](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-inkling-small.md)
- [Gemma 4 31B IT vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [Gemma 4 E2B IT vs Inkling-Small](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-inkling-small.md)
- [Gemma 4 E2B IT vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [Gemma 4 E4B IT vs Inkling-Small](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-inkling-small.md)
- [Gemma 4 E4B IT vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [GLM-4.5-Air vs Inkling-Small](https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling-small.md)
- [GLM-4.5-Air vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/glm-4-5-air-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [GLM-4.7-Flash vs Inkling-Small](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-inkling-small.md)
- [GLM-4.7-Flash vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [GLM-5.3-Flash vs Inkling-Small](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling-small.md)
- [GLM-5.3-Flash vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [GLM-5.3 vs Inkling-Small](https://www.anchorterminal.com/compare/glm-5-3-vs-inkling-small.md)
- [GLM-5.3 vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/glm-5-3-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [gpt-oss-120b vs Inkling-Small](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-inkling-small.md)
- [gpt-oss-120b vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [gpt-oss-20b vs Inkling-Small](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling-small.md)
- [gpt-oss-20b vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [Granite 4.2 3B vs Inkling-Small](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling-small.md)
- [Granite 4.2 3B vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [Hy3 vs Inkling-Small](https://www.anchorterminal.com/compare/hy3-vs-inkling-small.md)
- [Hy3 vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/hy3-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [Inkling-Small vs Kimi K3](https://www.anchorterminal.com/compare/inkling-small-vs-kimi-k3.md)
- [Inkling-Small vs Kolibri-1](https://www.anchorterminal.com/compare/inkling-small-vs-kolibri-1.md)
- [Inkling-Small vs Laguna M.1](https://www.anchorterminal.com/compare/inkling-small-vs-laguna-m-1.md)
- [Inkling-Small vs Laguna S 2.1](https://www.anchorterminal.com/compare/inkling-small-vs-laguna-s-2-1.md)
- [Inkling-Small vs Laguna XS 2.1](https://www.anchorterminal.com/compare/inkling-small-vs-laguna-xs-2-1.md)
- [Inkling-Small vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/inkling-small-vs-lfm2-5-2-6b.md)
- [Inkling-Small vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/inkling-small-vs-ling-3-0-tiny.md)
- [Inkling-Small vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/inkling-small-vs-mimo-v2-6-distill-qwen-9b.md)
- [Inkling-Small vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/inkling-small-vs-minicpm-o-4-5.md)
- [Inkling-Small vs MiniCPM5-2B](https://www.anchorterminal.com/compare/inkling-small-vs-minicpm5-2b.md)
- [Inkling-Small vs MiniMax-M2.5](https://www.anchorterminal.com/compare/inkling-small-vs-minimax-m2-5.md)
- [Inkling-Small vs MiniMax-M2.7](https://www.anchorterminal.com/compare/inkling-small-vs-minimax-m2-7.md)
- [Inkling-Small vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/inkling-small-vs-muse-glimmer-30b.md)
- [Inkling-Small vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/inkling-small-vs-nemotron-3-5-lightning-30b-a3b.md)
- [Inkling-Small vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/inkling-small-vs-nemotron-3-nano-30b-a3b.md)
- [Inkling-Small vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/inkling-small-vs-nemotron-3-nano-4b.md)
- [Inkling-Small vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/inkling-small-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)
- [Inkling-Small vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/inkling-small-vs-nemotron-3-super-120b-a12b.md)
- [Inkling-Small vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/inkling-small-vs-nemotron-3-ultra-550b-a55b.md)
- [Inkling-Small vs occamy-1.0](https://www.anchorterminal.com/compare/inkling-small-vs-occamy-1-0.md)
- [Inkling-Small vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/inkling-small-vs-olmo-3-7b-think.md)
- [Inkling-Small vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/inkling-small-vs-ornith-1-5-35b-a3b.md)
- [Inkling-Small vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/inkling-small-vs-ornith-1-5-397b.md)
- [Inkling-Small vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/inkling-small-vs-ornith-1-5-9b.md)
- [Inkling-Small vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-30b-a3b-instruct-2507.md)
- [Inkling-Small vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-4b-instruct-2507.md)
- [Inkling-Small vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-5-0-8b.md)
- [Inkling-Small vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-5-122b-a10b.md)
- [Inkling-Small vs Qwen3.5-2B](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-5-2b.md)
- [Inkling-Small vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-5-397b-a17b.md)
- [Inkling-Small vs Qwen3.5-4B](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-5-4b.md)
- [Inkling-Small vs Qwen3.5-9B](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-5-9b.md)
- [Inkling-Small vs Qwen3.6-27B](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-6-27b.md)
- [Inkling-Small vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-6-35b-a3b.md)
- [Inkling-Small vs Qwen3.8-27B](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-8-27b.md)
- [Inkling-Small vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-8-flash-next.md)
- [Inkling-Small vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-coder-30b-a3b-instruct.md)
- [Inkling-Small vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-coder-next.md)
- [Inkling-Small vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-omni-30b-a3b-instruct.md)
- [Inkling-Small vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-vl-2b-instruct.md)
- [Inkling-Small vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-vl-30b-a3b-instruct.md)
- [Inkling-Small vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-vl-32b-instruct.md)
- [Inkling-Small vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-vl-4b-instruct.md)
- [Inkling-Small vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/inkling-small-vs-qwen3-vl-8b-instruct.md)
- [Inkling-Small vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/inkling-small-vs-qwopus3-8-27b-flash-v2.md)
- [Inkling-Small vs SmolLM3-3B](https://www.anchorterminal.com/compare/inkling-small-vs-smollm3-3b.md)
- [Inkling-Small vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/inkling-small-vs-spark-x2-6-4b.md)
- [Inkling-Small vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/inkling-small-vs-swift-1-5-qwen3-8-27b.md)
- [Inkling-Small vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/inkling-small-vs-swift-1-5-qwen3-8-flash-next.md)
- [Inkling-Small vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/inkling-small-vs-thinkingcap-qwen3-8-27b.md)
- [Inkling vs Inkling-Small](https://www.anchorterminal.com/compare/inkling-vs-inkling-small.md)
- [Inkling vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/inkling-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Kimi K3](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-kimi-k3.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Kolibri-1](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-kolibri-1.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Laguna M.1](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-laguna-m-1.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Laguna S 2.1](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-laguna-s-2-1.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Laguna XS 2.1](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-laguna-xs-2-1.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-lfm2-5-2-6b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-ling-3-0-tiny.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-mimo-v2-6-distill-qwen-9b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-minicpm-o-4-5.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiniCPM5-2B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-minicpm5-2b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiniMax-M2.5](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-minimax-m2-5.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiniMax-M2.7](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-minimax-m2-7.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-muse-glimmer-30b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-nemotron-3-5-lightning-30b-a3b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-nemotron-3-nano-30b-a3b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-nemotron-3-nano-4b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-nemotron-3-super-120b-a12b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-nemotron-3-ultra-550b-a55b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs occamy-1.0](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-occamy-1-0.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-olmo-3-7b-think.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-ornith-1-5-35b-a3b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-ornith-1-5-397b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-ornith-1-5-9b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-30b-a3b-instruct-2507.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-4b-instruct-2507.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-5-0-8b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-5-122b-a10b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3.5-2B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-5-2b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-5-397b-a17b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3.5-4B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-5-4b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3.5-9B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-5-9b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3.6-27B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-6-27b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-6-35b-a3b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3.8-27B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-8-27b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-8-flash-next.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-coder-30b-a3b-instruct.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-coder-next.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-omni-30b-a3b-instruct.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-vl-2b-instruct.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-vl-30b-a3b-instruct.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-vl-32b-instruct.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-vl-4b-instruct.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwen3-vl-8b-instruct.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-qwopus3-8-27b-flash-v2.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs SmolLM3-3B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-smollm3-3b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-spark-x2-6-4b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-swift-1-5-qwen3-8-27b.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-swift-1-5-qwen3-8-flash-next.md)
- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-thinkingcap-qwen3-8-27b.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp