Model benchmarks
Ministral-3-3B-Instruct-2512-GGUF local LLM performance
As of October 2026, Ministral-3-3B-Instruct-2512-GGUF runs at up to 19.5 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
3B
Peak speed
19.5 tok/s
Average speed
18.9 tok/s
Avg PP
1607.4 tok/s
Min memory
n/a
Max context
16,384 tokens
Avg output / run
7,449 tokens
Avg runtime / run
7m 40s
Avg quality
49.9
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 | 45.2 | 49.9 | 54.6 |
| Agent Workflow | 28.6 | 43.7 | 58.9 |
| Code Generation | 37.3 | 41.6 | 45.9 |
| Role Play & Narrative | 48.3 | 57.4 | 66.4 |
| Research & Analysis | 48.7 | 57.0 | 65.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination Ministral-3-3B-Instruct-2512-GGUF 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 | Lemonade | — | 19.5 tok/s | 18.9 tok/s | n/a | 16,384 tokens | 49.9 | 2 |
Benchmark runs
All 2 Ministral-3-3B-Instruct-2512-GGUF 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 good for coding?
- In our benchmarks, Ministral-3-3B-Instruct-2512-GGUF scores 41.6/100 for coding. It runs at about 18.9 tok/s, so if you want more speed, IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V2.1-GGUF:1 is faster (~25.2 tok/s) and still scores well for coding (84.9/100).
- Is Ministral-3-3B-Instruct-2512-GGUF good for agentic (tool-using) tasks?
- In our benchmarks, Ministral-3-3B-Instruct-2512-GGUF scores 43.7/100 for agentic workflows. It runs at about 18.9 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 for local inference?
- Across 2 community benchmark runs, Ministral-3-3B-Instruct-2512-GGUF reaches up to 19.5 tok/s and averages 18.9 tok/s, with the fastest results on NVIDIA GeForce RTX 2050.
- Which tools have been used to run Ministral-3-3B-Instruct-2512-GGUF?
- Benchmarks were submitted using Lemonade. Results are community-contributed and updated as new runs arrive.