Model benchmarks
ministral-3b-instruct local LLM performance
As of October 2026, ministral-3b-instruct runs at up to 50.6 tok/s for local inference (best of 4 community benchmark runs across 1 GPU).
Model size
3B
Peak speed
50.6 tok/s
Average speed
31.6 tok/s
Avg PP
796.6 tok/s
Min memory
455 MB
Max context
16,384 tokens
Avg output / run
12,819 tokens
Avg runtime / run
14m 7s
Avg quality
1.9
Benchmark runs
4
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 4 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 | 1.5 | 1.9 | 2.3 |
| Agent Workflow | 2.4 | 3.5 | 5.3 |
| Code Generation | 0.0 | 0.2 | 0.5 |
| Role Play & Narrative | 0.3 | 2.5 | 5.0 |
| Research & Analysis | 0.2 | 1.5 | 3.1 |
Performance by hardware and tool
Every hardware/tool/quantization combination ministral-3b-instruct has been benchmarked on, ranked by peak token generation speed. Last updated October 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 2050 | LM Studio | Q4_K_M | 50.6 tok/s | 31.6 tok/s | 455 MB | 16,384 tokens | 1.9 | 4 |
Benchmark runs
All 4 ministral-3b-instruct runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is ministral-3b-instruct good for coding?
- In our benchmarks, ministral-3b-instruct scores 0.2/100 for coding. It runs at about 31.6 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 ministral-3b-instruct good for agentic (tool-using) tasks?
- In our benchmarks, ministral-3b-instruct scores 3.5/100 for agentic workflows. It runs at about 31.6 tok/s, so if you want more speed, Nex-N2.5-mini-APEX-Mini is faster (~88.2 tok/s) and still scores well for agentic workflows (91.3/100).
- How fast is ministral-3b-instruct for local inference?
- Across 4 community benchmark runs, ministral-3b-instruct reaches up to 50.6 tok/s and averages 31.6 tok/s, with the fastest results on NVIDIA GeForce RTX 2050.
- How much memory does ministral-3b-instruct need?
- The leanest observed configuration used about 455 MB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run ministral-3b-instruct?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.