Model benchmarks
swift-1.5-27b local LLM performance
As of November 2026, swift-1.5-27b runs at up to 98.1 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
27B
Peak speed
98.1 tok/s
Average speed
96.8 tok/s
Avg PP
2427.8 tok/s
Min memory
n/a
Max context
65,536 tokens
Avg output / run
48,796 tokens
Avg runtime / run
8m 4s
Avg quality
87.0
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 | 85.4 | 87.0 | 88.6 |
| Agent Workflow | 83.8 | 87.2 | 90.6 |
| Code Generation | 80.7 | 84.8 | 88.8 |
| Role Play & Narrative | 88.5 | 89.8 | 91.1 |
| Research & Analysis | 86.3 | 86.3 | 86.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination swift-1.5-27b 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 |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon AI PRO R9700 | radiance | — | 98.1 tok/s | 96.8 tok/s | n/a | 65,536 tokens | 87.0 | 2 |
Benchmark runs
All 2 swift-1.5-27b runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is swift-1.5-27b good for coding?
- In our benchmarks, swift-1.5-27b scores 84.8/100 for coding. It runs at about 96.8 tok/s, so if you want more speed, swift-1.5-27b-turbo is faster (~158.6 tok/s) and still scores well for coding (83.0/100).
- Is swift-1.5-27b good for agentic (tool-using) tasks?
- In our benchmarks, swift-1.5-27b scores 87.2/100 for agentic workflows. It runs at about 96.8 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 swift-1.5-27b for local inference?
- Across 2 community benchmark runs, swift-1.5-27b reaches up to 98.1 tok/s and averages 96.8 tok/s, with the fastest results on AMD Radeon AI PRO R9700.
- Which tools have been used to run swift-1.5-27b?
- Benchmarks were submitted using radiance. Results are community-contributed and updated as new runs arrive.