Model benchmarks
hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S local LLM performance
As of September 2026, hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S runs at up to 29.9 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
26.9B
Peak speed
29.9 tok/s
Average speed
24.2 tok/s
Avg PP
199.3 tok/s
Min memory
21.0 GB
Max context
180.000 tokens
Avg output / run
66.528 tokens
Avg runtime / run
49m 3s
Avg quality
85.2
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 | 84.7 | 85.2 | 85.8 |
| Agent Workflow | 87.6 | 89.1 | 90.6 |
| Code Generation | 73.5 | 74.0 | 74.4 |
| Role Play & Narrative | 90.0 | 92.1 | 94.1 |
| Research & Analysis | 83.8 | 85.8 | 87.8 |
Performance by hardware and tool
Every hardware/tool/quantization combination hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S has been benchmarked on, ranked by peak token generation speed. Last updated September 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 7900 XTX | Ollama | IQ3_S | 29.9 tok/s | 24.2 tok/s | 21.0 GB | 180.000 tokens | 85.2 | 2 |
Benchmark runs
All 2 hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S good for coding?
- In our benchmarks, hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S scores 74.0/100 for coding. It runs at about 24.2 tok/s, so if you want more speed, /home/polaris/models/Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL.gguf is faster (~35.6 tok/s) and still scores well for coding (84.9/100).
- Is hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S good for agentic (tool-using) tasks?
- In our benchmarks, hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S scores 89.1/100 for agentic workflows. It runs at about 24.2 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 hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S for local inference?
- Across 2 community benchmark runs, hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S reaches up to 29.9 tok/s and averages 24.2 tok/s, with the fastest results on AMD Radeon RX 7900 XTX.
- How much memory does hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S need?
- The leanest observed configuration used about 21.0 GB of memory (quantizations tested: IQ3_S).
- Which tools have been used to run hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S?
- Benchmarks were submitted using Ollama. Results are community-contributed and updated as new runs arrive.