Model benchmarks
qwen3.8-flash-next-unsloth-ud-iq4_xs local LLM performance
As of October 2026, qwen3.8-flash-next-unsloth-ud-iq4_xs runs at up to 51.2 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
51.2 tok/s
Average speed
48.0 tok/s
Avg PP
254.2 tok/s
Min memory
73.6 GB
Max context
262,144 tokens
Avg output / run
18,883 tokens
Avg runtime / run
6m 48s
Avg quality
74.9
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 | 65.8 | 74.9 | 83.9 |
| Agent Workflow | 81.1 | 83.9 | 86.7 |
| Code Generation | 6.3 | 40.8 | 75.2 |
| Role Play & Narrative | 91.7 | 92.4 | 93.1 |
| Research & Analysis | 77.2 | 82.5 | 87.8 |
Performance by hardware and tool
Every hardware/tool/quantization combination qwen3.8-flash-next-unsloth-ud-iq4_xs has been benchmarked on, ranked by peak token generation speed. Last updated October 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 9070/9070 XT/9070 GRE | Strata | — | 51.2 tok/s | 48.0 tok/s | 73.6 GB | 262,144 tokens | 74.9 | 2 |
Benchmark runs
All 2 qwen3.8-flash-next-unsloth-ud-iq4_xs runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is qwen3.8-flash-next-unsloth-ud-iq4_xs good for coding?
- In our benchmarks, qwen3.8-flash-next-unsloth-ud-iq4_xs scores 40.8/100 for coding. It runs at about 48.0 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 qwen3.8-flash-next-unsloth-ud-iq4_xs good for agentic (tool-using) tasks?
- In our benchmarks, qwen3.8-flash-next-unsloth-ud-iq4_xs scores 83.9/100 for agentic workflows. It runs at about 48.0 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 qwen3.8-flash-next-unsloth-ud-iq4_xs for local inference?
- Across 2 community benchmark runs, qwen3.8-flash-next-unsloth-ud-iq4_xs reaches up to 51.2 tok/s and averages 48.0 tok/s, with the fastest results on AMD Radeon RX 9070/9070 XT/9070 GRE.
- How much memory does qwen3.8-flash-next-unsloth-ud-iq4_xs need?
- The leanest observed configuration used about 73.6 GB of memory.
- Which tools have been used to run qwen3.8-flash-next-unsloth-ud-iq4_xs?
- Benchmarks were submitted using Strata. Results are community-contributed and updated as new runs arrive.