Can I run Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-Final-GGUF on an RTX 3090?
Yes, just
Its Hermes3.6-35B-A3B-Uncensored-Genesis-Final-MTP-APEX-Compact file (18.3 GB) fits in the 21.6 GB an RTX 3090 can use, with room for ≈ 152K tokens of context.
Full analysis of Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-Final-GGUF
Everything that runs on RTX 3090
Get the Hermes3.6-35B-A3B-Uncensored-Genesis-Final-MTP-APEX-Compact file on Hugging Face
ollama run hf.co/LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-Final-GGUFFiles and context on RTX 3090
Each file of Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-Final-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) |
|---|---|---|---|---|
| Q8_K | 43.6 GB | Doesn't fit | — | — |
| Hermes3.6-35B-A3B-Uncensored-Genesis-Final-MTP-APEX | 26.7 GB | Doesn't fit | — | — |
| Hermes3.6-35B-A3B-Uncensored-Genesis-Final-APEX | 25.8 GB | Doesn't fit | — | — |
| Hermes3.6-35B-A3B-Uncensored-Genesis-Final-MTP-APEX-Compact | 18.3 GB | Tight | 152K | 256K |
| Hermes3.6-35B-A3B-Uncensored-Genesis-Final-APEX-Compact | 17.4 GB | Tight | 195K | 256K |