Model benchmarks
Bonsai-8B-gguf local LLM performance
As of November 2026, Bonsai-8B-gguf runs at up to 65.7 tok/s for local inference (best of 4 community benchmark runs across 1 GPU).
Model size
8B
Peak speed
65.7 tok/s
Average speed
65.5 tok/s
Avg PP
917.7 tok/s
Min memory
n/a
Max context
65,536 tokens
Avg output / run
7,069 tokens
Avg runtime / run
1m 55s
Avg quality
39.8
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 | 33.0 | 39.8 | 48.4 |
| Agent Workflow | 17.1 | 47.5 | 79.3 |
| Code Generation | 9.6 | 12.8 | 18.2 |
| Role Play & Narrative | 48.5 | 55.3 | 63.2 |
| Research & Analysis | 34.3 | 43.7 | 54.7 |
Performance by hardware and tool
Every hardware/tool/quantization combination Bonsai-8B-gguf 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 | — | 65.7 tok/s | 65.5 tok/s | n/a | 65,536 tokens | 39.8 | 4 |
Benchmark runs
All 4 Bonsai-8B-gguf runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Bonsai-8B-gguf good for coding?
- In our benchmarks, Bonsai-8B-gguf scores 12.8/100 for coding. It runs at about 65.5 tok/s, so if you want more speed, turbo is faster (~124.1 tok/s) and still scores well for coding (85.3/100).
- Is Bonsai-8B-gguf good for agentic (tool-using) tasks?
- In our benchmarks, Bonsai-8B-gguf scores 47.5/100 for agentic workflows. It runs at about 65.5 tok/s, so if you want more speed, Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-i8KV-r21 is faster (~133.3 tok/s) and still scores well for agentic workflows (91.8/100).
- How fast is Bonsai-8B-gguf for local inference?
- Across 4 community benchmark runs, Bonsai-8B-gguf reaches up to 65.7 tok/s and averages 65.5 tok/s, with the fastest results on NVIDIA GeForce RTX 2050.
- Which tools have been used to run Bonsai-8B-gguf?
- Benchmarks were submitted using Lemonade. Results are community-contributed and updated as new runs arrive.