Model benchmarks
mimo-v2.6-distill-qwen-9b-optiq local LLM performance
As of November 2026, mimo-v2.6-distill-qwen-9b-optiq runs at up to 26.3 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
9B
Peak speed
26.3 tok/s
Average speed
26.2 tok/s
Avg PP
165.9 tok/s
Min memory
9.8 GB
Max context
32,768 tokens
Avg output / run
17,304 tokens
Avg runtime / run
11m 43s
Avg quality
56.1
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 | 47.9 | 56.1 | 64.2 |
| Agent Workflow | 18.0 | 47.3 | 76.6 |
| Code Generation | 38.3 | 42.1 | 45.9 |
| Role Play & Narrative | 53.6 | 64.7 | 75.8 |
| Research & Analysis | 59.6 | 70.1 | 80.6 |
Performance by hardware and tool
Every hardware/tool/quantization combination mimo-v2.6-distill-qwen-9b-optiq has been benchmarked on, ranked by peak token generation speed. Last updated November 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Apple M1 Pro | LM Studio | 4bit | 26.3 tok/s | 26.2 tok/s | 9.8 GB | 32,768 tokens | 56.1 | 2 |
Benchmark runs
All 2 mimo-v2.6-distill-qwen-9b-optiq 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-optiq good for coding?
- In our benchmarks, mimo-v2.6-distill-qwen-9b-optiq scores 42.1/100 for coding. It runs at about 26.2 tok/s, so if you want more speed, Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp is faster (~37.5 tok/s) and still scores well for coding (83.8/100).
- Is mimo-v2.6-distill-qwen-9b-optiq good for agentic (tool-using) tasks?
- In our benchmarks, mimo-v2.6-distill-qwen-9b-optiq scores 47.3/100 for agentic workflows. It runs at about 26.2 tok/s, so if you want more speed, muse-glimmer:latest is faster (~33.3 tok/s) and still scores well for agentic workflows (91.6/100).
- How fast is mimo-v2.6-distill-qwen-9b-optiq for local inference?
- Across 2 community benchmark runs, mimo-v2.6-distill-qwen-9b-optiq reaches up to 26.3 tok/s and averages 26.2 tok/s, with the fastest results on Apple M1 Pro.
- How much memory does mimo-v2.6-distill-qwen-9b-optiq need?
- The leanest observed configuration used about 9.8 GB of memory (quantizations tested: 4bit).
- Which tools have been used to run mimo-v2.6-distill-qwen-9b-optiq?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.