Model benchmarks
Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-MTP local LLM performance
As of November 2026, Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-MTP runs at up to 85.2 tok/s for local inference (best of 4 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
85.2 tok/s
Average speed
78.1 tok/s
Avg PP
940.3 tok/s
Min memory
n/a
Max context
65,536 tokens
Avg output / run
82,760 tokens
Avg runtime / run
17m 55s
Avg quality
87.1
Benchmark runs
4
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 4 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 | 84.9 | 87.1 | 89.4 |
| Agent Workflow | 87.9 | 91.3 | 93.3 |
| Code Generation | 69.6 | 76.3 | 82.2 |
| Role Play & Narrative | 90.0 | 94.0 | 96.4 |
| Research & Analysis | 83.1 | 86.7 | 90.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-MTP 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 AI PRO R9700 | Strata | — | 85.2 tok/s | 78.1 tok/s | n/a | 65,536 tokens | 87.1 | 4 |
Benchmark runs
All 4 Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-MTP runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-MTP good for coding?
- In our benchmarks, Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-MTP scores 76.3/100 for coding. It runs at about 78.1 tok/s, so if you want more speed, turbo is faster (~124.1 tok/s) and still scores well for coding (85.3/100).
- Is Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-MTP good for agentic (tool-using) tasks?
- In our benchmarks, Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-MTP scores 91.3/100 for agentic workflows. It runs at about 78.1 tok/s, so if you want more speed, Qwen3.8-27B-IQ5R-V4-DFlash2-TP2-i8KV-r21 is faster (~133.3 tok/s) and still scores well for agentic workflows (91.8/100).
- How fast is Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-MTP for local inference?
- Across 4 community benchmark runs, Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-MTP reaches up to 85.2 tok/s and averages 78.1 tok/s, with the fastest results on AMD Radeon AI PRO R9700.
- Which tools have been used to run Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-MTP?
- Benchmarks were submitted using Strata. Results are community-contributed and updated as new runs arrive.