Model benchmarks
prism-ml/Ternary-Bonsai-2-27B-gguf:TQ1_0 local LLM performance
As of October 2026, prism-ml/Ternary-Bonsai-2-27B-gguf:TQ1_0 runs at up to 58.2 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
27B
Peak speed
58.2 tok/s
Average speed
57.8 tok/s
Avg PP
1237.6 tok/s
Min memory
10.0 GB
Max context
131,072 tokens
Avg output / run
68,346 tokens
Avg runtime / run
21m 24s
Avg quality
82.4
Benchmark runs
2
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 2 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 | 81.3 | 82.4 | 83.5 |
| Agent Workflow | 90.4 | 90.4 | 90.4 |
| Code Generation | 75.3 | 76.7 | 78.0 |
| Role Play & Narrative | 79.3 | 81.0 | 82.7 |
| Research & Analysis | 80.1 | 81.5 | 83.0 |
Performance by hardware and tool
Every hardware/tool/quantization combination prism-ml/Ternary-Bonsai-2-27B-gguf:TQ1_0 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 | llama.cpp | Q1_0 | 58.2 tok/s | 57.8 tok/s | 10.0 GB | 131,072 tokens | 82.4 | 2 |
Benchmark runs
All 2 prism-ml/Ternary-Bonsai-2-27B-gguf:TQ1_0 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is prism-ml/Ternary-Bonsai-2-27B-gguf:TQ1_0 good for coding?
- In our benchmarks, prism-ml/Ternary-Bonsai-2-27B-gguf:TQ1_0 scores 76.7/100 for coding. It runs at about 57.8 tok/s, so if you want more speed, nvidia/Qwen3.8-27B-NVFP4 is faster (~75.5 tok/s) and still scores well for coding (83.5/100).
- Is prism-ml/Ternary-Bonsai-2-27B-gguf:TQ1_0 good for agentic (tool-using) tasks?
- In our benchmarks, prism-ml/Ternary-Bonsai-2-27B-gguf:TQ1_0 scores 90.4/100 for agentic workflows. It runs at about 57.8 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 prism-ml/Ternary-Bonsai-2-27B-gguf:TQ1_0 for local inference?
- Across 2 community benchmark runs, prism-ml/Ternary-Bonsai-2-27B-gguf:TQ1_0 reaches up to 58.2 tok/s and averages 57.8 tok/s, with the fastest results on NVIDIA GeForce RTX 4070.
- How much memory does prism-ml/Ternary-Bonsai-2-27B-gguf:TQ1_0 need?
- The leanest observed configuration used about 10.0 GB of memory (quantizations tested: Q1_0).
- Which tools have been used to run prism-ml/Ternary-Bonsai-2-27B-gguf:TQ1_0?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.