Model benchmarks
qwen38-daily:latest local LLM performance
As of November 2026, qwen38-daily:latest runs at up to 26.7 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
27.3B
Peak speed
26.7 tok/s
Average speed
26.1 tok/s
Avg PP
302.1 tok/s
Min memory
15.1 GB
Max context
32,768 tokens
Avg output / run
17,153 tokens
Avg runtime / run
11m 5s
Avg quality
81.9
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 | 79.4 | 81.9 | 84.3 |
| Agent Workflow | 77.5 | 79.1 | 80.6 |
| Code Generation | 74.8 | 79.8 | 84.8 |
| Role Play & Narrative | 74.1 | 82.6 | 91.0 |
| Research & Analysis | 84.0 | 86.1 | 88.2 |
Performance by hardware and tool
Every hardware/tool/quantization combination qwen38-daily:latest 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 7600 XT | Ollama | IQ3_S | 26.7 tok/s | 26.1 tok/s | 15.1 GB | 32,768 tokens | 81.9 | 2 |
Benchmark runs
All 2 qwen38-daily:latest runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is qwen38-daily:latest good for coding?
- In our benchmarks, qwen38-daily:latest scores 79.8/100 for coding. It runs at about 26.1 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 qwen38-daily:latest good for agentic (tool-using) tasks?
- In our benchmarks, qwen38-daily:latest scores 79.1/100 for agentic workflows. It runs at about 26.1 tok/s, so if you want more speed, muse-glimmer:latest is faster (~33.3 tok/s) and still scores well for agentic workflows (91.6/100).
- How fast is qwen38-daily:latest for local inference?
- Across 2 community benchmark runs, qwen38-daily:latest reaches up to 26.7 tok/s and averages 26.1 tok/s, with the fastest results on AMD Radeon RX 7600 XT.
- How much memory does qwen38-daily:latest need?
- The leanest observed configuration used about 15.1 GB of memory (quantizations tested: IQ3_S).
- Which tools have been used to run qwen38-daily:latest?
- Benchmarks were submitted using Ollama. Results are community-contributed and updated as new runs arrive.