Can I run MiMo-V2.6-Distill-Qwen-9B on an RTX 4080?
Yes, with a GGUF version
The published weights are too big, but the Q8_0 file from bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF (9.55 GB) fits, with room for ≈ 143K tokens of context.
Full analysis of MiMo-V2.6-Distill-Qwen-9B
Everything that runs on RTX 4080
Get the Q8_0 file on Hugging Face
ollama run hf.co/bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q8_0Files and context on RTX 4080
Each file of MiMo-V2.6-Distill-Qwen-9B (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 4080 | Context (16-bit) | Context (8-bit) |
|---|---|---|---|---|
| As published | 18.8 GB | Doesn't fit | — | — |
| BF16 | 17.9 GB | Doesn't fit | — | — |
| Q8_0 | 9.55 GB | Fits | 143K | 256K |
| Q6_K_L | 8.11 GB | Fits | 186K | 256K |
| Q6_K | 7.79 GB | Fits | 195K | 256K |
| Q6_K_S | 7.51 GB | Fits | 204K | 256K |
| Q5_K_M | 6.88 GB | Fits | 223K | 256K |
| Q5_K_S | 6.50 GB | Fits | 234K | 256K |
| Q4_K_L | 6.20 GB | Fits | 243K | 256K |
| Q4_1 | 5.94 GB | Fits | 250K | 256K |
| Q4_K_M | 5.84 GB | Fits | 254K | 256K |
| IQ4_NL | 5.83 GB | Fits | 254K | 256K |
| Q4_K_S | 5.48 GB | Fits | 256K | 256K |
| Q4_0 | 5.48 GB | Fits | 256K | 256K |
| IQ4_XS | 5.23 GB | Fits | 256K | 256K |
| IQ3_M | 4.85 GB | Fits | 256K | 256K |
| Q3_K_L | 4.66 GB | Fits | 256K | 256K |
| Q3_K_M | 4.48 GB | Fits | 256K | 256K |
| IQ3_XS | 4.27 GB | Fits | 256K | 256K |
| Q3_K_S | 4.26 GB | Fits | 256K | 256K |
| IQ3_XXS | 4.14 GB | Fits | 256K | 256K |
| Q2_K | 3.64 GB | Fits | 256K | 256K |
| IQ2_M | 3.54 GB | Fits | 256K | 256K |
| Q8_0 | 9.53 GB | Fits | 144K | 256K |