bartowski
MiMo V2.6 Distill Qwen 9B
MiMo V2.6 Distill Qwen 9B is a 8.95B dense qwen35 model from bartowski. Configured context length is 262,144 tokens. Quant sizes are the GGUF file bytes published on Hugging Face when a file exists.
Parameters9.0B
Context256K
Attentionhybrid
Licensesee the repo
32 layers · 4 KV heads · head dim 256 · 24 linear-attention layers · GGUF repo · config
Quant file sizes
| Quant | File size | Source |
|---|---|---|
| BF16 | 16.7 GB | Hugging Face file bytes |
| Q8_0 | 8.89 GB | Hugging Face file bytes |
| Q6_K | 21.8 GB | Hugging Face file bytes |
| Q5_K_M | 6.40 GB | Hugging Face file bytes |
| Q5_K_S | 6.05 GB | Hugging Face file bytes |
| Q4_K_M | 5.44 GB | Hugging Face file bytes |
| Q4_K_S | 5.11 GB | Hugging Face file bytes |
| IQ4_NL | 5.43 GB | Hugging Face file bytes |
| IQ4_XS | 4.87 GB | Hugging Face file bytes |
| Q4_1 | 5.54 GB | Hugging Face file bytes |
| Q4_0 | 5.11 GB | Hugging Face file bytes |
| Q3_K_L | 4.34 GB | Hugging Face file bytes |
| Q3_K_M | 4.17 GB | Hugging Face file bytes |
| IQ3_M | 4.51 GB | Hugging Face file bytes |
| Q3_K_S | 3.97 GB | Hugging Face file bytes |
| IQ3_XXS | 3.85 GB | Hugging Face file bytes |
| Q2_K | 3.39 GB | Hugging Face file bytes |
On common machines
| Device | Verdict | Quant | Speed |
|---|---|---|---|
| GeForce RTX 4060 Ti 8GB | Tight fit | Q5_K_M | 23–31 |
| GeForce RTX 3060 12GB | Tight fit | Q8_0 | 20–28 |
| GeForce RTX 4060 Ti 16GB | Runs | Q8_0 | 16–22 |
| GeForce RTX 4090 | Runs | BF16 | 30–42 |
| GeForce RTX 5090 | Runs great | BF16 | 54–74 |
| Apple M4 Pro | Tight fit | BF16 | 8.3–11 |
| Apple M5 | Tight fit | Q8_0 | 8.6–12 |
| CPU only · DDR5-5600 | Runs on CPU | BF16 | 2.7–3.7 |
Smallest devices that fit it fully
- GeForce RTX 3050 6GB — Tight fit, Q3_K_L, 19–26 tok/s
- GeForce RTX 2060 6GB — Tight fit, Q3_K_L, 38–51 tok/s
- GeForce GTX 1660 Super — Tight fit, Q3_K_L, 38–51 tok/s
- GeForce GTX 1660 Ti — Tight fit, Q3_K_L, 32–44 tok/s
- Intel Arc A380 — Tight fit, Q3_K_L, 21–28 tok/s
- GeForce RTX 5060 Ti 8GB — Tight fit, Q5_K_M, 35–48 tok/s
Run it
Commands for the GeForce RTX 4060 Ti 16GB estimate (Q8_0).
llama.cpp
llama-server -hf bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q8_0 -c 8192 -ngl 32
No matching name in the Ollama library snapshot.
LM Studio
lms get bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF # Then load quant Q8_0