Model benchmarks
Sage-A1.5_t1p95k20m0P15 local LLM performance
As of November 2026, Sage-A1.5_t1p95k20m0P15 runs at up to 93.3 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
93.3 tok/s
Average speed
93.0 tok/s
Avg PP
421.2 tok/s
Min memory
53.3 GB
Max context
32,768 tokens
Avg output / run
33,254 tokens
Avg runtime / run
6m 10s
Avg quality
75.9
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 | 72.2 | 75.9 | 79.7 |
| Agent Workflow | 77.6 | 82.1 | 86.6 |
| Code Generation | 68.9 | 70.2 | 71.5 |
| Role Play & Narrative | 68.6 | 73.7 | 78.8 |
| Research & Analysis | 73.6 | 77.8 | 81.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination Sage-A1.5_t1p95k20m0P15 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 | — | 93.3 tok/s | 93.0 tok/s | 53.3 GB | 32,768 tokens | 75.9 | 2 |
Benchmark runs
All 2 Sage-A1.5_t1p95k20m0P15 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Sage-A1.5_t1p95k20m0P15 good for coding?
- In our benchmarks, Sage-A1.5_t1p95k20m0P15 scores 70.2/100 for coding. It runs at about 93.0 tok/s, so if you want more speed, Qwen3.6-35B-A3B-Q4_K_XL is faster (~156.9 tok/s) and still scores well for coding (82.2/100).
- Is Sage-A1.5_t1p95k20m0P15 good for agentic (tool-using) tasks?
- In our benchmarks, Sage-A1.5_t1p95k20m0P15 scores 82.1/100 for agentic workflows. It runs at about 93.0 tok/s, so if you want more speed, swift-1.5-qwen3.8-flash-next-iq3_s is faster (~259.0 tok/s) and still scores well for agentic workflows (88.9/100).
- How fast is Sage-A1.5_t1p95k20m0P15 for local inference?
- Across 2 community benchmark runs, Sage-A1.5_t1p95k20m0P15 reaches up to 93.3 tok/s and averages 93.0 tok/s, with the fastest results on Tesla V100-PCIE-32GB.
- How much memory does Sage-A1.5_t1p95k20m0P15 need?
- The leanest observed configuration used about 53.3 GB of memory.
- Which tools have been used to run Sage-A1.5_t1p95k20m0P15?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.