Model benchmarks
prism-ml/Ternary-Bonsai-1.7B-gguf local LLM performance
As of November 2026, prism-ml/Ternary-Bonsai-1.7B-gguf runs at up to 38.1 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
1.7B
Peak speed
38.1 tok/s
Average speed
37.8 tok/s
Avg PP
354.1 tok/s
Min memory
2.8 GB
Max context
32,768 tokens
Avg output / run
7,066 tokens
Avg runtime / run
3m 32s
Avg quality
29.1
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 | 26.6 | 29.1 | 31.2 |
| Agent Workflow | 45.3 | 56.2 | 65.6 |
| Code Generation | 0.2 | 1.6 | 3.2 |
| Role Play & Narrative | 36.9 | 39.3 | 42.0 |
| Research & Analysis | 17.4 | 19.5 | 21.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination prism-ml/Ternary-Bonsai-1.7B-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 |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon Vega Series / Radeon Vega Mobile Series | Unsloth Studio | Q2_0_g64 | 38.1 tok/s | 37.8 tok/s | 2.8 GB | 32,768 tokens | 29.1 | 3 |
Benchmark runs
All 3 prism-ml/Ternary-Bonsai-1.7B-gguf runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is prism-ml/Ternary-Bonsai-1.7B-gguf good for coding?
- In our benchmarks, prism-ml/Ternary-Bonsai-1.7B-gguf scores 1.6/100 for coding. It runs at about 37.8 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 prism-ml/Ternary-Bonsai-1.7B-gguf good for agentic (tool-using) tasks?
- In our benchmarks, prism-ml/Ternary-Bonsai-1.7B-gguf scores 56.2/100 for agentic workflows. It runs at about 37.8 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-1.7B-gguf for local inference?
- Across 3 community benchmark runs, prism-ml/Ternary-Bonsai-1.7B-gguf reaches up to 38.1 tok/s and averages 37.8 tok/s, with the fastest results on AMD Radeon Vega Series / Radeon Vega Mobile Series.
- How much memory does prism-ml/Ternary-Bonsai-1.7B-gguf need?
- The leanest observed configuration used about 2.8 GB of memory (quantizations tested: Q2_0_g64).
- Which tools have been used to run prism-ml/Ternary-Bonsai-1.7B-gguf?
- Benchmarks were submitted using Unsloth Studio. Results are community-contributed and updated as new runs arrive.