Model benchmarks
nanbeige4.1-3b local LLM performance
As of July 2026, nanbeige4.1-3b runs at up to 73.3 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
3B
Peak speed
73.3 tok/s
Average speed
71.9 tok/s
Min memory
n/a
Max context
65,536 tokens
Avg quality
49.9
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 | 29.7 | 49.9 | 62.6 |
| Agent Workflow | 33.2 | 60.5 | 84.0 |
| Code Generation | 0.6 | 14.4 | 34.0 |
| Role Play & Narrative | 12.4 | 52.8 | 76.5 |
| Research & Analysis | 70.5 | 71.8 | 72.8 |
Performance by hardware and tool
Every hardware/tool/quantization combination nanbeige4.1-3b has been benchmarked on, ranked by peak token generation speed. Last updated July 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 4070 Ti SUPER | LM Studio | — | 73.3 tok/s | 71.9 tok/s | n/a | 65,536 tokens | 49.8 | 3 |
Benchmark runs
All 3 nanbeige4.1-3b runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is nanbeige4.1-3b good for coding?
- In our benchmarks, nanbeige4.1-3b scores 14.4/100 for coding. It runs at about 71.9 tok/s, so if you want more speed, ornith-ai/Ornith-1.5-35B-A3B-GGUF is faster (~90.8 tok/s) and still scores well for coding (83.8/100).
- Is nanbeige4.1-3b good for agentic (tool-using) tasks?
- In our benchmarks, nanbeige4.1-3b scores 60.5/100 for agentic workflows. It runs at about 71.9 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 nanbeige4.1-3b for local inference?
- Across 3 community benchmark runs, nanbeige4.1-3b reaches up to 73.3 tok/s and averages 71.9 tok/s, with the fastest results on NVIDIA GeForce RTX 4070 Ti SUPER.
- Which tools have been used to run nanbeige4.1-3b?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.