Model benchmarks
qwen3.8-flash-next-unsloth-ud-q2_0 local LLM performance
As of November 2026, qwen3.8-flash-next-unsloth-ud-q2_0 runs at up to 70.6 tok/s for local inference (best of 4 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
70.6 tok/s
Average speed
66.7 tok/s
Avg PP
216.5 tok/s
Min memory
57.5 GB
Max context
65,536 tokens
Avg output / run
25,959 tokens
Avg runtime / run
6m 57s
Avg quality
68.6
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 | 62.4 | 68.6 | 74.4 |
| Agent Workflow | 10.4 | 58.8 | 88.8 |
| Code Generation | 18.8 | 54.3 | 70.8 |
| Role Play & Narrative | 78.3 | 86.8 | 95.9 |
| Research & Analysis | 58.2 | 74.7 | 87.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination qwen3.8-flash-next-unsloth-ud-q2_0 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 7900 XT | Strata | Q2_0 | 70.6 tok/s | 66.7 tok/s | 57.5 GB | 65,536 tokens | 68.6 | 4 |
Benchmark runs
All 4 qwen3.8-flash-next-unsloth-ud-q2_0 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-q2_0 good for coding?
- In our benchmarks, qwen3.8-flash-next-unsloth-ud-q2_0 scores 54.3/100 for coding. It runs at about 66.7 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-unsloth-ud-q2_0 good for agentic (tool-using) tasks?
- In our benchmarks, qwen3.8-flash-next-unsloth-ud-q2_0 scores 58.8/100 for agentic workflows. It runs at about 66.7 tok/s, so if you want more speed, qwen3.8-flash-next-ud-iq4_xs-v31-q8-engram is faster (~82.6 tok/s) and still scores well for agentic workflows (91.6/100).
- How fast is qwen3.8-flash-next-unsloth-ud-q2_0 for local inference?
- Across 4 community benchmark runs, qwen3.8-flash-next-unsloth-ud-q2_0 reaches up to 70.6 tok/s and averages 66.7 tok/s, with the fastest results on AMD Radeon RX 7900 XT.
- How much memory does qwen3.8-flash-next-unsloth-ud-q2_0 need?
- The leanest observed configuration used about 57.5 GB of memory (quantizations tested: Q2_0).
- Which tools have been used to run qwen3.8-flash-next-unsloth-ud-q2_0?
- Benchmarks were submitted using Strata. Results are community-contributed and updated as new runs arrive.