Model benchmarks
openbmb/MiniCPM5-1B-GGUF local LLM performance
As of October 2026, openbmb/MiniCPM5-1B-GGUF runs at up to 236.1 tok/s for local inference (best of 3 community benchmark runs across 2 GPUs).
Model size
1B
Peak speed
236.1 tok/s
Average speed
128.4 tok/s
Avg PP
3773.3 tok/s
Min memory
4.0 GB
Max context
131,072 tokens
Avg output / run
15,719 tokens
Avg runtime / run
2m 32s
Avg quality
14.1
Benchmark runs
3
GPUs tested
2
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 | 12.8 | 14.1 | 15.5 |
| Agent Workflow | 21.1 | 22.1 | 23.0 |
| Code Generation | 0.0 | 0.5 | 1.3 |
| Role Play & Narrative | 21.3 | 23.5 | 24.9 |
| Research & Analysis | 8.0 | 10.2 | 13.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination openbmb/MiniCPM5-1B-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 4070 | Unsloth Studio | Q8_0 | 236.1 tok/s | 236.1 tok/s | 4.0 GB | 131,072 tokens | 12.7 | 1 |
| Intel(R) Arc(TM) 140V GPU (16GB) | Unsloth Studio | — | 85.6 tok/s | 74.5 tok/s | n/a | 8,192 tokens | 14.7 | 2 |
Benchmark runs
All 3 openbmb/MiniCPM5-1B-GGUF runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is openbmb/MiniCPM5-1B-GGUF good for agentic (tool-using) tasks?
- In our benchmarks, openbmb/MiniCPM5-1B-GGUF scores 22.1/100 for agentic workflows. It runs at about 128.4 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-MLX-oQ4e-MTP is faster (~151.8 tok/s) and still scores well for agentic workflows (83.0/100).
- How fast is openbmb/MiniCPM5-1B-GGUF for local inference?
- Across 3 community benchmark runs, openbmb/MiniCPM5-1B-GGUF reaches up to 236.1 tok/s and averages 128.4 tok/s, with the fastest results on NVIDIA GeForce RTX 4070.
- How much memory does openbmb/MiniCPM5-1B-GGUF need?
- The leanest observed configuration used about 4.0 GB of memory (quantizations tested: Q8_0).
- Which tools have been used to run openbmb/MiniCPM5-1B-GGUF?
- Benchmarks were submitted using Unsloth Studio. Results are community-contributed and updated as new runs arrive.