Can I run Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF on an RTX 3090?
Yes, just
Its Huihui-Qwen3.6-35B-A3B-abliterated-patch-all-0 file (19.9 GB) fits in the 21.6 GB an RTX 3090 can use, with room for ≈ 77K tokens of context.
Full analysis of Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF
Everything that runs on RTX 3090
Get the Huihui-Qwen3.6-35B-A3B-abliterated-patch-all-0 file on Hugging Face
ollama run hf.co/huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUFFiles and context on RTX 3090
Each file of Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.
| File | Size | On RTX 3090 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| F16 | 71.1 GB | Doesn't fit | — | — |
| Q8_0 | 37.8 GB | Doesn't fit | — | — |
| Q6_K | 29.2 GB | Doesn't fit | — | — |
| Q5_K | 25.3 GB | Doesn't fit | — | — |
| Q4_K | 21.7 GB | Doesn't fit | — | — |
| Huihui-Qwen3.6-35B-A3B-abliterated-patch-all-0 | 19.9 GB | Tight | 77K | 153K |
| Huihui-Qwen3.6-35B-A3B-abliterated-patch-all-2 | 17.7 GB | Tight | 182K | 256K |
| Huihui-Qwen3.6-35B-A3B-abliterated-patch-all-3 | 17.7 GB | Tight | 182K | 256K |
| Huihui-Qwen3.6-35B-A3B-abliterated-patch-all-1 | 17.7 GB | Tight | 182K | 256K |
| Q3_K | 17.2 GB | Fits | 208K | 256K |
| Huihui-Qwen3.6-35B-A3B-abliterated-patch-all-4 | 14.0 GB | Fits | 256K | 256K |
| Q2_K | 13.2 GB | Fits | 256K | 256K |