Model benchmarks
Sabi-Noema_t1p95k20m0 local LLM performance
As of November 2026, Sabi-Noema_t1p95k20m0 runs at up to 59.4 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
59.4 tok/s
Average speed
58.9 tok/s
Avg PP
677.3 tok/s
Min memory
60.6 GB
Max context
32,768 tokens
Avg output / run
31,899 tokens
Avg runtime / run
8m 44s
Avg quality
85.9
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 | 85.7 | 85.9 | 86.2 |
| Agent Workflow | 91.2 | 91.2 | 91.3 |
| Code Generation | 76.5 | 77.3 | 78.1 |
| Role Play & Narrative | 91.2 | 91.8 | 92.3 |
| Research & Analysis | 82.8 | 83.5 | 84.2 |
Performance by hardware and tool
Every hardware/tool/quantization combination Sabi-Noema_t1p95k20m0 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 |
|---|---|---|---|---|---|---|---|---|
| Tesla V100-PCIE-32GB | llama.cpp | — | 59.4 tok/s | 58.9 tok/s | 60.6 GB | 32,768 tokens | 85.9 | 2 |
Benchmark runs
All 2 Sabi-Noema_t1p95k20m0 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Sabi-Noema_t1p95k20m0 good for coding?
- In our benchmarks, Sabi-Noema_t1p95k20m0 scores 77.3/100 for coding. It runs at about 58.9 tok/s, so if you want more speed, unsloth/Qwen3.8-27B-GGUF:IQ3_S is faster (~104.3 tok/s) and still scores well for coding (83.0/100).
- Is Sabi-Noema_t1p95k20m0 good for agentic (tool-using) tasks?
- In our benchmarks, Sabi-Noema_t1p95k20m0 scores 91.2/100 for agentic workflows. It runs at about 58.9 tok/s, so if you want more speed, granite-4.2-8b-Q4_K_L is faster (~71.6 tok/s) and still scores well for agentic workflows (92.9/100).
- How fast is Sabi-Noema_t1p95k20m0 for local inference?
- Across 2 community benchmark runs, Sabi-Noema_t1p95k20m0 reaches up to 59.4 tok/s and averages 58.9 tok/s, with the fastest results on Tesla V100-PCIE-32GB.
- How much memory does Sabi-Noema_t1p95k20m0 need?
- The leanest observed configuration used about 60.6 GB of memory.
- Which tools have been used to run Sabi-Noema_t1p95k20m0?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.