Model benchmarks
Swift-1.5-Ornith-9B-Q4_K_M local LLM performance
As of November 2026, Swift-1.5-Ornith-9B-Q4_K_M runs at up to 47.0 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
9B
Peak speed
47.0 tok/s
Average speed
43.4 tok/s
Avg PP
644.3 tok/s
Min memory
9.2 GB
Max context
131,072 tokens
Avg output / run
29,833 tokens
Avg runtime / run
12m 25s
Avg quality
78.9
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 | 77.3 | 78.9 | 80.5 |
| Agent Workflow | 73.1 | 77.4 | 81.6 |
| Code Generation | 58.4 | 66.9 | 75.5 |
| Role Play & Narrative | 84.8 | 84.9 | 84.9 |
| Research & Analysis | 84.6 | 86.6 | 88.5 |
Performance by hardware and tool
Every hardware/tool/quantization combination Swift-1.5-Ornith-9B-Q4_K_M 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 |
|---|---|---|---|---|---|---|---|---|
| Advanced Micro Devices, Inc. [AMD/ATI] HawkPoint1 | llama.cpp | Q4_K_M | 47.0 tok/s | 43.4 tok/s | 9.2 GB | 131,072 tokens | 78.9 | 2 |
Benchmark runs
All 2 Swift-1.5-Ornith-9B-Q4_K_M runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Swift-1.5-Ornith-9B-Q4_K_M good for coding?
- In our benchmarks, Swift-1.5-Ornith-9B-Q4_K_M scores 66.9/100 for coding. It runs at about 43.4 tok/s, so if you want more speed, Inkling-2-Mini-oQ4e-mtp is faster (~57.7 tok/s) and still scores well for coding (83.9/100).
- Is Swift-1.5-Ornith-9B-Q4_K_M good for agentic (tool-using) tasks?
- In our benchmarks, Swift-1.5-Ornith-9B-Q4_K_M scores 77.4/100 for agentic workflows. It runs at about 43.4 tok/s, so if you want more speed, Nex-N2.5-mini-APEX-Mini is faster (~88.2 tok/s) and still scores well for agentic workflows (91.3/100).
- How fast is Swift-1.5-Ornith-9B-Q4_K_M for local inference?
- Across 2 community benchmark runs, Swift-1.5-Ornith-9B-Q4_K_M reaches up to 47.0 tok/s and averages 43.4 tok/s, with the fastest results on Advanced Micro Devices, Inc. [AMD/ATI] HawkPoint1.
- How much memory does Swift-1.5-Ornith-9B-Q4_K_M need?
- The leanest observed configuration used about 9.2 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run Swift-1.5-Ornith-9B-Q4_K_M?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.