Model benchmarks
MiMo-V2.6-Distill-Qwen-9B-Q6_K local LLM performance
As of September 2026, MiMo-V2.6-Distill-Qwen-9B-Q6_K runs at up to 64.2 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
9B
Peak speed
64.2 tok/s
Average speed
58.7 tok/s
Avg PP
1571.9 tok/s
Min memory
4.4 GB
Max context
262.144 tokens
Avg output / run
21.185 tokens
Avg runtime / run
6m 38s
Avg quality
70.3
Benchmark runs
2
GPUs tested
1
Quality by task
Average LLM-judged quality (0–100) with the run-to-run spread shown as a P5–P95 band, overall and for each benchmark task, across all 2 runs. The low and high columns show how much the judge’s score varies between runs, and need at least two runs to display.
| Task | P5 (low) | Avg | P95 (high) |
|---|---|---|---|
| Overall | 67.3 | 70.3 | 73.2 |
| Agent Workflow | 25.4 | 41.4 | 57.3 |
| Code Generation | 61.9 | 66.6 | 71.3 |
| Role Play & Narrative | 82.6 | 85.5 | 88.4 |
| Research & Analysis | 84.3 | 87.6 | 90.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination MiMo-V2.6-Distill-Qwen-9B-Q6_K has been benchmarked on, ranked by peak token generation speed. Last updated September 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 5060 | llama.cpp | Q6_K | 64.2 tok/s | 58.7 tok/s | 4.4 GB | 262.144 tokens | 70.3 | 2 |
Benchmark runs
All 2 MiMo-V2.6-Distill-Qwen-9B-Q6_K runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is MiMo-V2.6-Distill-Qwen-9B-Q6_K good for coding?
- In our benchmarks, MiMo-V2.6-Distill-Qwen-9B-Q6_K scores 66.6/100 for coding. It runs at about 58.7 tok/s, so if you want more speed, unsloth/Qwen3.8-27B-GGUF:IQ3_S is faster (~104.3 tok/s) and still scores well for coding (83.0/100).
- Is MiMo-V2.6-Distill-Qwen-9B-Q6_K good for agentic (tool-using) tasks?
- In our benchmarks, MiMo-V2.6-Distill-Qwen-9B-Q6_K scores 41.4/100 for agentic workflows. It runs at about 58.7 tok/s, so if you want more speed, granite-4.2-8b-Q4_K_L is faster (~71.6 tok/s) and still scores well for agentic workflows (92.9/100).
- How fast is MiMo-V2.6-Distill-Qwen-9B-Q6_K for local inference?
- Across 2 community benchmark runs, MiMo-V2.6-Distill-Qwen-9B-Q6_K reaches up to 64.2 tok/s and averages 58.7 tok/s, with the fastest results on NVIDIA GeForce RTX 5060.
- How much memory does MiMo-V2.6-Distill-Qwen-9B-Q6_K need?
- The leanest observed configuration used about 4.4 GB of memory (quantizations tested: Q6_K).
- Which tools have been used to run MiMo-V2.6-Distill-Qwen-9B-Q6_K?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.