Can I run MiMo-V2.6-Distill-Qwen-9B-GGUF on an RTX 4060?
Yes, just
Its Q5_K_M file (6.88 GB) fits in the 7.20 GB an RTX 4060 can use, with room for ≈ 8K tokens of context.
Full analysis of MiMo-V2.6-Distill-Qwen-9B-GGUF
Everything that runs on RTX 4060
Get the Q5_K_M file on Hugging Face
ollama run hf.co/bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q5_K_MFiles and context on RTX 4060
Each file of MiMo-V2.6-Distill-Qwen-9B-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 4060 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| BF16 | 17.9 GB | Doesn't fit | — | — |
| Q8_0 | 9.55 GB | Doesn't fit | — | — |
| Q6_K_L | 8.11 GB | Doesn't fit | — | — |
| Q6_K | 7.79 GB | Doesn't fit | — | — |
| Q6_K_S | 7.51 GB | Doesn't fit | — | — |
| Q5_K_M | 6.88 GB | Tight | 8K | 16K |
| Q5_K_S | 6.50 GB | Tight | 19K | 39K |
| Q4_K_L | 6.20 GB | Tight | 28K | 56K |
| Q4_1 | 5.94 GB | Tight | 36K | 72K |
| Q4_K_M | 5.84 GB | Tight | 39K | 78K |
| IQ4_NL | 5.83 GB | Tight | 39K | 79K |
| Q4_K_S | 5.48 GB | Fits | 50K | 99K |
| Q4_0 | 5.48 GB | Fits | 50K | 99K |
| IQ4_XS | 5.23 GB | Fits | 57K | 115K |
| IQ3_M | 4.85 GB | Fits | 69K | 137K |
| Q3_K_L | 4.66 GB | Fits | 74K | 148K |
| Q3_K_M | 4.48 GB | Fits | 80K | 159K |
| IQ3_XS | 4.27 GB | Fits | 86K | 172K |
| Q3_K_S | 4.26 GB | Fits | 86K | 172K |
| IQ3_XXS | 4.14 GB | Fits | 90K | 179K |
| Q2_K | 3.64 GB | Fits | 104K | 209K |
| IQ2_M | 3.54 GB | Fits | 108K | 215K |