# Open-weight models you download and run yourself

> 3 open-weight models ranked by the Anchor benchmark. Leader Kolibri-1 (BB). Model weights you download and run on your own hardware, under a licence that says what you may do with them. Each is graded on the files, apart from any hosted API that serves the same model. Compared on the licence, the runtimes that load it, tool calling, context, the memory it needs and what the vendor publishes about training data and evaluations.

- Canonical: https://www.anchorterminal.com/categories/open-weights
- Markdown: https://www.anchorterminal.com/categories/open-weights.md (~1,450 tokens)
- Slim: https://www.anchorterminal.com/categories/open-weights.min.md (~280 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/categories/open-weights.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: 2026-10-20

Model weights you download and run on your own hardware, under a licence that says what you may do with them. Each is graded on the files, apart from any hosted API that serves the same model. Compared on the licence, the runtimes that load it, tool calling, context, the memory it needs and what the vendor publishes about training data and evaluations.

- Tools ranked: 3 · agent-ready (BB or better): 1 · accept x402: 0 · hosted endpoints: 0 · desk reviews by the panel: 12
- JSON: https://www.anchorterminal.com/api/v1/tools.json (list) · https://www.anchorterminal.com/api/v1/rankings.json (ranked) · https://www.anchorterminal.com/api/v1/x402.json (payable) · https://www.anchorterminal.com/api/v1/capabilities.json (by capability)
- Grades run AA, A, BB, B, C, D, E, F · methodology: https://www.anchorterminal.com/benchmark/

- Head-to-head comparisons (3): https://www.anchorterminal.com/compare/open-weights/index.md
- Capabilities in this category: model.open-weights
- https://letme.dev/model.open-weights picks the top-graded tool in this list and says how to call it direct (https://www.anchorterminal.com/letme/index.md)

## Ranking

| # | Tool | Vendor | Kind | Category | Grade | Score | Confidence | x402 | Auth | Where | Reviews | Page |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 47 | Kolibri-1 | Aleph Alpha | Open-weight model | Open weights | BB | 75.8 | medium | no | None | local | 3.5/5 (4) | https://www.anchorterminal.com/tools/kolibri-1.md |
| 428 | Qwen3.8-27B | Alibaba (Qwen team) | Open-weight model | Open weights | B | 63.7 | medium | no | None | local | 3/5 (4) | https://www.anchorterminal.com/tools/qwen3-8-27b.md |
| 472 | DeepSeek V4.1 Flash | DeepSeek | Open-weight model | Open weights | B | 62.8 | medium | no | None | local | 2.8/5 (4) | https://www.anchorterminal.com/tools/deepseek-v4-1-flash.md |

Scores are from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/), with Performance and Task success pending. p95 latency and context cost come from our probes, which haven't run yet.

## Summaries

### 47. Kolibri-1, BB (75.8)

Kolibri-1 is Aleph Alpha's open-weight mixture-of-experts reasoning model for German and English, 78B parameters with 3.46B active per token, published on Hugging Face in FP8 and BF16 under Apache 2.0 and served with vLLM. Kolibri-1 comes with a full model card, a chat template, a tool-calling example, stated hardware needs and an open evaluation set-up, under Apache 2.0 with no acceptable use policy. It runs through Aleph Alpha's vLLM plugin or Transformers 5.20.0, about 78 GB at FP8, and no safety results are published.

- Page: https://www.anchorterminal.com/tools/kolibri-1 · Markdown: https://www.anchorterminal.com/tools/kolibri-1.md · JSON: https://www.anchorterminal.com/api/v1/tools/kolibri-1.json
- Capabilities: model.open-weights

### 428. Qwen3.8-27B, B (63.7)

Qwen3.8-27B is Alibaba's open-weight dense vision-language model of 27B parameters, with thinking on by default and a 262,144-token context, published on Hugging Face in BF16 and FP8 under Apache 2.0. Qwen3.8-27B runs nearly anywhere, in vLLM, SGLang, llama.cpp, Ollama and MLX, with an 18 GB Ollama build and Apache 2.0 terms. The card leaves out tool calling, hardware needs, training data, limitations and safety results, the files haven't changed since 14 August, and Alibaba answered none of the 40 most recent discussions.

- Page: https://www.anchorterminal.com/tools/qwen3-8-27b · Markdown: https://www.anchorterminal.com/tools/qwen3-8-27b.md · JSON: https://www.anchorterminal.com/api/v1/tools/qwen3-8-27b.json
- Capabilities: model.open-weights

### 472. DeepSeek V4.1 Flash, B (62.8)

DeepSeek V4.1 Flash is DeepSeek's open-weight multimodal mixture-of-experts model, 552B backbone parameters with 8B active in prefill and 16B in decode and a 1M-token context, published on Hugging Face under MIT. The 17 October update is graded. DeepSeek V4.1 Flash gives a 1M-token context, trained tool calls and an effort budget from 1 to 100 under the MIT licence, with every release kept in its own repository. It needs 510 GB of files and runs in vLLM or mlx-lm, prompts come from DeepSeek's code rather than a template, and no safety results or training sources are published.

- Page: https://www.anchorterminal.com/tools/deepseek-v4-1-flash · Markdown: https://www.anchorterminal.com/tools/deepseek-v4-1-flash.md · JSON: https://www.anchorterminal.com/api/v1/tools/deepseek-v4-1-flash.json
- Capabilities: model.open-weights

## How we test this category

In this run, public evidence against the open-weight reading of the checklist, from the model card, the files, the licence and the runtimes' own code. When our local runs start, each model that fits in 128 GB is served on one machine through llama.cpp and vLLM at the largest precision that fits. We measure tokens per second and time to first token, then run the agent task suite with the model driving. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.


---

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