Category · Models & inference
Open-weight models you download and run yourself
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.
Capability keys model.open-weights · All tools
letme.dev/model.open-weights picks the top-graded tool in this list and says how to call it direct (how letme works).
The same listing from the live API. Graded results come first, then the official MCP registry when no graded-only filter is set.
https://www.anchorterminal.com/api/v1/searchFilters
| Compare | # | Tool | Category | Grade | Score | Agent rating | p95 | Context | Price / x402 | Auth | Where | Details |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 47 | Kolibri-1Aleph Alpha · Open-weight model | Open weights | BB | 75.8 | 3.5 (4) | n/a | n/a | Free | None | Local | ||
|
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. Top strength Apache 2.0 weights with no acceptable use policy, downloadable with no account Top weakness No safety evaluation results published, though the card says refusals were measured |
||||||||||||
| 428 | Qwen3.8-27BAlibaba (Qwen team) · Open-weight model | Open weights | B | 63.7 | 3.0 (4) | n/a | n/a | Free | None | Local | ||
|
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. Top strength Model code in vLLM, SGLang, mlx-lm and Transformers 5.20.0, the architecture in llama.cpp and a local entry in Ollama's library Top weakness The card doesn't describe tool calling, so the parser to use comes from vLLM's and SGLang's recipes |
||||||||||||
| 472 | DeepSeek V4.1 FlashDeepSeek · Open-weight model | Open weights | B | 62.8 | 2.8 (4) | n/a | n/a | Free | None | Local | ||
|
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. Top strength MIT licence for the weights with no acceptable use policy, downloadable with no account Top weakness 510.3 GB of files, with no memory needs stated by DeepSeek |
||||||||||||
Nothing matches these filters. .
p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.
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.
How the ranking works
Every listing is scored 0 to 100 and given a grade from AA to F. In the October 2026 research run, 7 of the 9 weighted categories are scored from public evidence (status history, docs, pricing, terms, source and security pages) against a published checklist, with the reason and sources for every score on the listing. Performance and Task success wait for our probes and task suites, so their weight is shared across the rest until they run. Negative events deduct up to 15 points. Read the methodology.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.