unsloth/LFM2.5-1.2B-Instruct-GGUF

Text Generation • 1B • Updated Jan 6 • 4.98k • 38

Note 145 t/s @ Q8_0. Surprisingly capable in chat. Not usable in OpenCode.

ggml-org/gpt-oss-20b-GGUF

21B • Updated Oct 30, 2025 • 85.6k • 142

Note 60 t/s @ MXFP4. OpenCode tools work. Prefer 120B.

mradermacher/Nanbeige4.1-3B-GGUF

4B • Updated Feb 12 • 2.63k • 37

Note 51 t/s @ Q8_0. Thinks for minutes. Not usable in OpenCode.

unsloth/GLM-4.7-Flash-GGUF

Text Generation • 30B • Updated Feb 12 • 127k • 601

Note 45 t/s @ Q8_0. OpenCode tool calling works great. Made a nice looking 400-line OpenMeteo weather app with typeahead search. Required manual TypeScript error fixes to run. Note that the smaller REAP model wasn't faster.

bartowski/moonshotai_Kimi-Linear-48B-A3B-Instruct-GGUF

Text Generation • 49B • Updated Feb 9 • 3.46k • 19

Note 45 t/s @ Q8_0. Excellent OpenCode tool calling including todo list and ask question. Made a 600-line OpenMeteo weather app with no errors. Note that it did everything the frontend-design skill said NOT to do, resulting in a comically bad looking app. Still, most usable local model on this list.

unsloth/Qwen3.5-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated Mar 5 • 1.34M • 818

Note TBD

Intel/Qwen3.5-122B-A10B-gguf-q2ks-mixed-AutoRound

122B • Updated 24 days ago • 871 • 5

Note TBD

ggml-org/gpt-oss-120b-GGUF

117B • Updated Oct 30, 2025 • 341k • 71

Note 42 t/s @ MXFP4. Good OpenCode tool calling, writes working TypeScript, but even the frontend-design skill can't get it to make attractive websites. Feels like GPT-4o, which is nice for nostalgia.

unsloth/Qwen3-Coder-Next-GGUF

Text Generation • 80B • Updated Mar 6 • 207k • 578

Note 32 t/s @ Q8_0. Was not able to build a working OpenMeteo weather app. Struggled with the edit tool attempting to fix errors. Was not able to properly trace errors in the code.

Intel/MiniMax-M2-REAP-172B-A10B-gguf-q2ks-mixed-AutoRound

173B • Updated Feb 9 • 164 • 13

Note 26 t/s @ Q2_K_S. Good chat performance. Didn't try in OpenCode. Interesting quantization.

Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF

Image-Text-to-Text • 9B • Updated 10 days ago • 263k • 291

Note 22 t/s @ Q8_0. Perfect tool calling in OpenCode. Fetched the OpenMeteo API schema from GitHub, initialized a Vite project, and made a multi-file React SPA with no errors. Outputs a stray closing /think tag after every response.

unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF

24B • Updated Dec 15, 2025 • 35.6k • 127

Note 9 t/s @ Q8_0. All dense models are slow on Strix Halo. Speculative decoding (ngram-mod) works very well when it kicks in.

Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF

Image-Text-to-Text • 27B • Updated 10 days ago • 398k • 567

Note 8/ts @ Q8_0. Too slow to try OpenCode. Notably didn't overthink on anything. Otherwise, same comments as Devstral 24B.