Model benchmarks
qwen3.8-flash-next-unsloth-ud-iq3_xxs local LLM performance
As of November 2026, qwen3.8-flash-next-unsloth-ud-iq3_xxs runs at up to 65.8 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
65.8 tok/s
Average speed
58.6 tok/s
Avg PP
329.9 tok/s
Min memory
37.0 GB
Max context
65,536 tokens
Avg output / run
61,214 tokens
Avg runtime / run
16m 59s
Avg quality
84.1
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 | 83.3 | 84.1 | 84.9 |
| Agent Workflow | 89.4 | 89.9 | 90.4 |
| Code Generation | 62.7 | 68.5 | 74.4 |
| Role Play & Narrative | 86.0 | 89.4 | 92.9 |
| Research & Analysis | 88.5 | 88.6 | 88.7 |
Performance by hardware and tool
Every hardware/tool/quantization combination qwen3.8-flash-next-unsloth-ud-iq3_xxs 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 |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 3090 | Strata | — | 65.8 tok/s | 58.6 tok/s | 37.0 GB | 65,536 tokens | 84.1 | 2 |
Benchmark runs
All 2 qwen3.8-flash-next-unsloth-ud-iq3_xxs 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-iq3_xxs good for coding?
- In our benchmarks, qwen3.8-flash-next-unsloth-ud-iq3_xxs scores 68.5/100 for coding. It runs at about 58.6 tok/s, so if you want more speed, swift-1.5-27b is faster (~96.8 tok/s) and still scores well for coding (84.8/100).
- Is qwen3.8-flash-next-unsloth-ud-iq3_xxs good for agentic (tool-using) tasks?
- In our benchmarks, qwen3.8-flash-next-unsloth-ud-iq3_xxs scores 89.9/100 for agentic workflows. It runs at about 58.6 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-iq3_xxs for local inference?
- Across 2 community benchmark runs, qwen3.8-flash-next-unsloth-ud-iq3_xxs reaches up to 65.8 tok/s and averages 58.6 tok/s, with the fastest results on NVIDIA GeForce RTX 3090.
- How much memory does qwen3.8-flash-next-unsloth-ud-iq3_xxs need?
- The leanest observed configuration used about 37.0 GB of memory.
- Which tools have been used to run qwen3.8-flash-next-unsloth-ud-iq3_xxs?
- Benchmarks were submitted using Strata. Results are community-contributed and updated as new runs arrive.