Leaderboard / Xiaomi (MiMo)
MiMo-V2.6-Distill-Qwen-9B
Xiaomi (MiMo) · MiMo-V2.6 · released 2026-09 · data checked 2026-11-01 Needs verification
MiMo-V2.6-Distill-Qwen-9B is a 9.4B-parameter dense model from Xiaomi (MiMo) (China), released 2026-09 under the MIT license. It doesn't have enough reported benchmarks for an index score yet. It needs about 7.5 GB of memory at 4-bit with an 8K-token context.
Distilled from MiMo-V2.6-Flash. Released as a starting point for RL research.
Benchmarks
Each bar shows this model's score. The tick marks the best small model on that benchmark.
No benchmark results for this release yet. Know of one? Send it.
Specifications
- Lab
- Xiaomi (MiMo) (CN · China)
- Architecture
- Dense transformer
- Total parameters
- 9.4B
- Active parameters
- All (dense)
- Size class
- Small
- Context window
- 262K tokens
- Input modalities
- text
- Reasoning
- Reasoning (thinking)
- License
- MIT
- Openness
- Open weights
- Memory to run
- ~7.5 GB at 4-bit, 8K context (more sizes)
Compare with
- MiMo-V2.6-Distill-Qwen-9B vs MiniCPM-SALA (9.5B, index 52.6)
- MiMo-V2.6-Distill-Qwen-9B vs Qwen3.5 9B (9B, index 63.9)
- MiMo-V2.6-Distill-Qwen-9B vs Nemotron Nano 9B v2 (8.9B, index 52.5)
Sources
Something wrong here? Report it.
Run it locally
No quantized build from a well-known publisher yet; check the model card for instructions.
Memory needed: weights, context cache and runtime buffers (context cache estimated: attention layout not published).
| Quantization | 4K context | 32K context | 256K context |
|---|---|---|---|
| 16-bit F16 | 20 GB | 24 GB | 57 GB |
| 8-bit Q8_0 | 11 GB | 15 GB | 48 GB |
| 4-bit Q4_K_M | 7.0 GB | 11 GB | 43 GB |