Model benchmarks
Swift-Qwen3.8-27B-GGUF-Q6_K local LLM performance
As of November 2026, Swift-Qwen3.8-27B-GGUF-Q6_K runs at up to 25.1 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
27B
Peak speed
25.1 tok/s
Average speed
24.8 tok/s
Avg PP
506.2 tok/s
Min memory
34.3 GB
Max context
262,144 tokens
Avg output / run
40,851 tokens
Avg runtime / run
27m 57s
Avg quality
83.3
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 | 82.2 | 83.3 | 84.3 |
| Agent Workflow | 84.5 | 86.7 | 89.0 |
| Code Generation | 72.4 | 74.6 | 76.8 |
| Role Play & Narrative | 82.4 | 87.1 | 91.7 |
| Research & Analysis | 84.3 | 84.8 | 85.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination Swift-Qwen3.8-27B-GGUF-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 |
|---|---|---|---|---|---|---|---|---|
| NVIDIA RTX A6000 | llama.cpp | Q6_K | 25.1 tok/s | 24.8 tok/s | 34.3 GB | 262,144 tokens | 83.3 | 2 |
Benchmark runs
All 2 Swift-Qwen3.8-27B-GGUF-Q6_K runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Swift-Qwen3.8-27B-GGUF-Q6_K good for coding?
- In our benchmarks, Swift-Qwen3.8-27B-GGUF-Q6_K scores 74.6/100 for coding. It runs at about 24.8 tok/s, so if you want more speed, local-qwen is faster (~60.2 tok/s) and still scores well for coding (84.8/100).
- Is Swift-Qwen3.8-27B-GGUF-Q6_K good for agentic (tool-using) tasks?
- In our benchmarks, Swift-Qwen3.8-27B-GGUF-Q6_K scores 86.7/100 for agentic workflows. It runs at about 24.8 tok/s, so if you want more speed, granite-4.2-8b-Q4_K_L is faster (~71.6 tok/s) and still scores well for agentic workflows (92.9/100).
- How fast is Swift-Qwen3.8-27B-GGUF-Q6_K for local inference?
- Across 2 community benchmark runs, Swift-Qwen3.8-27B-GGUF-Q6_K reaches up to 25.1 tok/s and averages 24.8 tok/s, with the fastest results on NVIDIA RTX A6000.
- How much memory does Swift-Qwen3.8-27B-GGUF-Q6_K need?
- The leanest observed configuration used about 34.3 GB of memory (quantizations tested: Q6_K).
- Which tools have been used to run Swift-Qwen3.8-27B-GGUF-Q6_K?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.