Model benchmarks
ternary-bonsai-2-27b local LLM performance
As of November 2026, ternary-bonsai-2-27b runs at up to 28.1 tok/s for local inference (best of 3 community benchmark runs across 2 GPUs).
Model size
27B
Peak speed
28.1 tok/s
Average speed
25.4 tok/s
Avg PP
371.0 tok/s
Min memory
9.8 GB
Max context
65,536 tokens
Avg output / run
46,330 tokens
Avg runtime / run
34m 29s
Avg quality
68.2
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 | 64.9 | 68.2 | 72.0 |
| Agent Workflow | 82.2 | 84.8 | 89.3 |
| Code Generation | 2.1 | 19.2 | 43.2 |
| Role Play & Narrative | 82.9 | 88.4 | 92.4 |
| Research & Analysis | 72.0 | 80.5 | 85.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination ternary-bonsai-2-27b 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 4070 | LM Studio | — | 28.1 tok/s | 28.1 tok/s | 9.8 GB | 65,536 tokens | 64.6 | 1 |
| NVIDIA GeForce RTX 3080 Laptop GPU | LM Studio | Q2_0 | 26.1 tok/s | 24.1 tok/s | 14.0 GB | 65,536 tokens | 70.1 | 2 |
Benchmark runs
All 3 ternary-bonsai-2-27b runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is ternary-bonsai-2-27b good for coding?
- In our benchmarks, ternary-bonsai-2-27b scores 19.2/100 for coding. It runs at about 25.4 tok/s, so if you want more speed, Huihui-Qwen3.8-27B-abliterated-Swift-1.5-GSQ-RCO-IQ3_S-mtp is faster (~43.5 tok/s) and still scores well for coding (86.6/100).
- Is ternary-bonsai-2-27b good for agentic (tool-using) tasks?
- In our benchmarks, ternary-bonsai-2-27b scores 84.8/100 for agentic workflows. It runs at about 25.4 tok/s, so if you want more speed, muse-glimmer:latest is faster (~33.3 tok/s) and still scores well for agentic workflows (91.6/100).
- How fast is ternary-bonsai-2-27b for local inference?
- Across 3 community benchmark runs, ternary-bonsai-2-27b reaches up to 28.1 tok/s and averages 25.4 tok/s, with the fastest results on NVIDIA GeForce RTX 4070.
- How much memory does ternary-bonsai-2-27b need?
- The leanest observed configuration used about 9.8 GB of memory (quantizations tested: Q2_0).
- Which tools have been used to run ternary-bonsai-2-27b?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.