Model benchmarks
swift-1.5-9b-q8_0 local LLM performance
As of November 2026, swift-1.5-9b-q8_0 runs at up to 32.2 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
9B
Peak speed
32.2 tok/s
Average speed
32.1 tok/s
Avg PP
1423.6 tok/s
Min memory
16.4 GB
Max context
200,000 tokens
Avg output / run
37,357 tokens
Avg runtime / run
19m 35s
Avg quality
77.2
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 | 73.0 | 77.2 | 79.8 |
| Agent Workflow | 78.4 | 86.4 | 92.9 |
| Code Generation | 37.4 | 49.3 | 60.8 |
| Role Play & Narrative | 84.4 | 86.0 | 88.7 |
| Research & Analysis | 84.2 | 87.1 | 90.5 |
Performance by hardware and tool
Every hardware/tool/quantization combination swift-1.5-9b-q8_0 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 | Q8_0 | 32.2 tok/s | 32.1 tok/s | 16.4 GB | 200,000 tokens | 77.2 | 3 |
Benchmark runs
All 3 swift-1.5-9b-q8_0 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is swift-1.5-9b-q8_0 good for coding?
- In our benchmarks, swift-1.5-9b-q8_0 scores 49.3/100 for coding. It runs at about 32.1 tok/s, so if you want more speed, Qwen3.8-27B-Turbo-Brilliance-50X-RI-GSQ-RCO-IQ3_XXS-mtp is faster (~37.5 tok/s) and still scores well for coding (83.8/100).
- Is swift-1.5-9b-q8_0 good for agentic (tool-using) tasks?
- In our benchmarks, swift-1.5-9b-q8_0 scores 86.4/100 for agentic workflows. It runs at about 32.1 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-q8_0 for local inference?
- Across 3 community benchmark runs, swift-1.5-9b-q8_0 reaches up to 32.2 tok/s and averages 32.1 tok/s, with the fastest results on AMD Radeon RX 9050 / 9060 XT.
- How much memory does swift-1.5-9b-q8_0 need?
- The leanest observed configuration used about 16.4 GB of memory (quantizations tested: Q8_0).
- Which tools have been used to run swift-1.5-9b-q8_0?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.