Model benchmarks
Ministral-3-3B-Instruct-2512-GGUF-Q8_0 local LLM performance
As of November 2026, Ministral-3-3B-Instruct-2512-GGUF-Q8_0 runs at up to 11.5 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
3B
Peak speed
11.5 tok/s
Average speed
11.3 tok/s
Avg PP
1119.7 tok/s
Min memory
n/a
Max context
32,768 tokens
Avg output / run
5,783 tokens
Avg runtime / run
9m 13s
Avg quality
41.6
Benchmark runs
3
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 3 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 | 41.2 | 41.6 | 41.9 |
| Agent Workflow | 40.3 | 44.4 | 48.8 |
| Code Generation | 21.2 | 24.3 | 28.4 |
| Role Play & Narrative | 53.0 | 58.5 | 62.6 |
| Research & Analysis | 37.7 | 39.0 | 40.4 |
Performance by hardware and tool
Every hardware/tool/quantization combination Ministral-3-3B-Instruct-2512-GGUF-Q8_0 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 |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 2050 | Lemonade | Q8_0 | 11.5 tok/s | 11.3 tok/s | n/a | 32,768 tokens | 41.6 | 3 |
Benchmark runs
All 3 Ministral-3-3B-Instruct-2512-GGUF-Q8_0 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Ministral-3-3B-Instruct-2512-GGUF-Q8_0 good for coding?
- In our benchmarks, Ministral-3-3B-Instruct-2512-GGUF-Q8_0 scores 24.3/100 for coding. It runs at about 11.3 tok/s, so if you want more speed, byteshape/Qwen3.8-27B-GGUF:IQ4_XS-ASCII-Condensed is faster (~42.0 tok/s) and still scores well for coding (86.3/100).
- Is Ministral-3-3B-Instruct-2512-GGUF-Q8_0 good for agentic (tool-using) tasks?
- In our benchmarks, Ministral-3-3B-Instruct-2512-GGUF-Q8_0 scores 44.4/100 for agentic workflows. It runs at about 11.3 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 Ministral-3-3B-Instruct-2512-GGUF-Q8_0 for local inference?
- Across 3 community benchmark runs, Ministral-3-3B-Instruct-2512-GGUF-Q8_0 reaches up to 11.5 tok/s and averages 11.3 tok/s, with the fastest results on NVIDIA GeForce RTX 2050.
- Which tools have been used to run Ministral-3-3B-Instruct-2512-GGUF-Q8_0?
- Benchmarks were submitted using Lemonade. Results are community-contributed and updated as new runs arrive.