Model benchmarks
openbmb/MiniCPM-V-4.7-35B-A3B-gguf local LLM performance
As of October 2026, openbmb/MiniCPM-V-4.7-35B-A3B-gguf runs at up to 59.0 tok/s for local inference (best of 4 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
59.0 tok/s
Average speed
51.8 tok/s
Avg PP
688.1 tok/s
Min memory
n/a
Max context
8,192 tokens
Avg output / run
8,869 tokens
Avg runtime / run
3m 13s
Avg quality
73.7
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 | 69.2 | 73.7 | 76.3 |
| Agent Workflow | 80.0 | 83.3 | 88.4 |
| Code Generation | 62.7 | 66.7 | 72.5 |
| Role Play & Narrative | 63.9 | 73.3 | 81.7 |
| Research & Analysis | 63.9 | 71.7 | 78.1 |
Performance by hardware and tool
Every hardware/tool/quantization combination openbmb/MiniCPM-V-4.7-35B-A3B-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 3070 Ti | Unsloth Studio | Q4_K_M | 59.0 tok/s | 57.7 tok/s | n/a | 8,192 tokens | 73.0 | 3 |
| NVIDIA GeForce RTX 3070 Ti | Unsloth Studio | Q6_K | 34.0 tok/s | 34.0 tok/s | n/a | 8,192 tokens | 76.1 | 1 |
Benchmark runs
All 4 openbmb/MiniCPM-V-4.7-35B-A3B-gguf runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is openbmb/MiniCPM-V-4.7-35B-A3B-gguf good for coding?
- In our benchmarks, openbmb/MiniCPM-V-4.7-35B-A3B-gguf scores 66.7/100 for coding. It runs at about 51.8 tok/s, so if you want more speed, local-qwen is faster (~60.2 tok/s) and still scores well for coding (84.8/100).
- Is openbmb/MiniCPM-V-4.7-35B-A3B-gguf good for agentic (tool-using) tasks?
- In our benchmarks, openbmb/MiniCPM-V-4.7-35B-A3B-gguf scores 83.3/100 for agentic workflows. It runs at about 51.8 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 openbmb/MiniCPM-V-4.7-35B-A3B-gguf for local inference?
- Across 4 community benchmark runs, openbmb/MiniCPM-V-4.7-35B-A3B-gguf reaches up to 59.0 tok/s and averages 51.8 tok/s, with the fastest results on NVIDIA GeForce RTX 3070 Ti.
- Which tools have been used to run openbmb/MiniCPM-V-4.7-35B-A3B-gguf?
- Benchmarks were submitted using Unsloth Studio. Results are community-contributed and updated as new runs arrive.