Model benchmarks
qwen3.8-flash-next-unsloth-ud-q3_k_xl local LLM performance
As of November 2026, qwen3.8-flash-next-unsloth-ud-q3_k_xl runs at up to 60.6 tok/s for local inference (best of 2 community benchmark runs across 2 GPUs).
Model size
Unknown
Peak speed
60.6 tok/s
Average speed
54.4 tok/s
Avg PP
231.4 tok/s
Min memory
67.0 GB
Max context
163,840 tokens
Avg output / run
42,523 tokens
Avg runtime / run
12m 31s
Avg quality
80.0
Benchmark runs
2
GPUs tested
2
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 | 78.5 | 80.0 | 81.6 |
| Agent Workflow | 80.8 | 83.7 | 86.6 |
| Code Generation | 52.1 | 63.5 | 74.9 |
| Role Play & Narrative | 85.9 | 86.4 | 86.9 |
| Research & Analysis | 84.8 | 86.6 | 88.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination qwen3.8-flash-next-unsloth-ud-q3_k_xl 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 | Q3_K | 60.6 tok/s | 60.6 tok/s | 80.1 GB | 163,840 tokens | 78.3 | 1 |
| AMD Radeon RX 7900 XT | Strata | Q3_K | 48.2 tok/s | 48.2 tok/s | 67.0 GB | 65,536 tokens | 81.8 | 1 |
Benchmark runs
All 2 qwen3.8-flash-next-unsloth-ud-q3_k_xl 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-q3_k_xl good for coding?
- In our benchmarks, qwen3.8-flash-next-unsloth-ud-q3_k_xl scores 63.5/100 for coding. It runs at about 54.4 tok/s, so if you want more speed, swift-1.5-27b is faster (~98.7 tok/s) and still scores well for coding (84.8/100).
- Is qwen3.8-flash-next-unsloth-ud-q3_k_xl good for agentic (tool-using) tasks?
- In our benchmarks, qwen3.8-flash-next-unsloth-ud-q3_k_xl scores 83.7/100 for agentic workflows. It runs at about 54.4 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-q3_k_xl for local inference?
- Across 2 community benchmark runs, qwen3.8-flash-next-unsloth-ud-q3_k_xl reaches up to 60.6 tok/s and averages 54.4 tok/s, with the fastest results on NVIDIA GeForce RTX 3090.
- How much memory does qwen3.8-flash-next-unsloth-ud-q3_k_xl need?
- The leanest observed configuration used about 67.0 GB of memory (quantizations tested: Q3_K).
- Which tools have been used to run qwen3.8-flash-next-unsloth-ud-q3_k_xl?
- Benchmarks were submitted using Strata. Results are community-contributed and updated as new runs arrive.