MiMo-V2.6-Distill-Qwen-9B-GGUF
Model details: - Parameter count: 9B - Input support: text, image (with mmproj file) - details - Speculative decoding: no - imatrix: yes - details
Params
9.0 B
Context
—
Downloads 30d
920 K
Likes
164
Download history
daily snapshots · 7 days920 K795 K
Oct 18Oct 20Oct 22Oct 24
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| MiMo-V2.6-Distill-Qwen-9B-IQ2_M.gguf | IQ2_M | 3.5 GB | 5.7 GB | ✅ Runs comfortably |
| MiMo-V2.6-Distill-Qwen-9B-Q2_K.gguf | Q2_K | 3.6 GB | 5.9 GB | ✅ Runs comfortably |
| MiMo-V2.6-Distill-Qwen-9B-IQ3_XXS.gguf | IQ3_XXS | 4.1 GB | 6.4 GB | ✅ Runs comfortably |
| MiMo-V2.6-Distill-Qwen-9B-IQ3_XS.gguf | IQ3_XS | 4.3 GB | 6.5 GB | ✅ Runs comfortably |
| MiMo-V2.6-Distill-Qwen-9B-Q3_K_L.gguf | Q3_K_L | 4.7 GB | 7.0 GB | ✅ Runs comfortably |
| MiMo-V2.6-Distill-Qwen-9B-IQ3_M.gguf | IQ3_M | 4.8 GB | 7.2 GB | ✅ Runs comfortably |
| MiMo-V2.6-Distill-Qwen-9B-IQ4_XS.gguf | IQ4_XS | 5.2 GB | 7.6 GB | ✅ Runs comfortably |
| MiMo-V2.6-Distill-Qwen-9B-IQ4_NL.gguf | IQ4_NL | 5.8 GB | 8.3 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Parameters
- 9.0 B
- First seen on the Hub
- 2026-09-21
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-18
Compare with any image-text-to-text model