Model benchmarks
swift-1.5-9b-q6_k local LLM performance
As of November 2026, swift-1.5-9b-q6_k runs at up to 39.7 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
9B
Peak speed
39.7 tok/s
Average speed
39.7 tok/s
Avg PP
1297.1 tok/s
Min memory
13.9 GB
Max context
200,000 tokens
Avg output / run
33,431 tokens
Avg runtime / run
14m 13s
Avg quality
74.4
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 | 66.2 | 74.4 | 82.2 |
| Agent Workflow | 30.3 | 64.1 | 86.8 |
| Code Generation | 52.6 | 66.4 | 76.5 |
| Role Play & Narrative | 80.5 | 82.7 | 84.3 |
| Research & Analysis | 83.8 | 84.3 | 84.8 |
Performance by hardware and tool
Every hardware/tool/quantization combination swift-1.5-9b-q6_k 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 RX 9050 / 9060 XT | llama.cpp | Q6_K | 39.7 tok/s | 39.7 tok/s | 13.9 GB | 200,000 tokens | 74.4 | 3 |
Benchmark runs
All 3 swift-1.5-9b-q6_k runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is swift-1.5-9b-q6_k good for coding?
- In our benchmarks, swift-1.5-9b-q6_k scores 66.4/100 for coding. It runs at about 39.7 tok/s, so if you want more speed, nvidia/Qwen3.8-27B-NVFP4 is faster (~63.3 tok/s) and still scores well for coding (82.7/100).
- Is swift-1.5-9b-q6_k good for agentic (tool-using) tasks?
- In our benchmarks, swift-1.5-9b-q6_k scores 64.1/100 for agentic workflows. It runs at about 39.7 tok/s, so if you want more speed, swift-iq2_xs is faster (~91.5 tok/s) and still scores well for agentic workflows (91.4/100).
- How fast is swift-1.5-9b-q6_k for local inference?
- Across 3 community benchmark runs, swift-1.5-9b-q6_k reaches up to 39.7 tok/s and averages 39.7 tok/s, with the fastest results on AMD Radeon RX 9050 / 9060 XT.
- How much memory does swift-1.5-9b-q6_k need?
- The leanest observed configuration used about 13.9 GB of memory (quantizations tested: Q6_K).
- Which tools have been used to run swift-1.5-9b-q6_k?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.