Model benchmarks
qwen3.8-35b-miniplus local LLM performance
As of October 2026, qwen3.8-35b-miniplus runs at up to 78.2 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
35B
Peak speed
78.2 tok/s
Average speed
77.9 tok/s
Avg PP
751.6 tok/s
Min memory
21.7 GB
Max context
65,536 tokens
Avg output / run
9,264 tokens
Avg runtime / run
1m 56s
Avg quality
73.7
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 | 72.2 | 73.7 | 75.1 |
| Agent Workflow | 71.3 | 77.8 | 84.3 |
| Code Generation | 66.6 | 70.9 | 75.3 |
| Role Play & Narrative | 67.8 | 70.3 | 72.8 |
| Research & Analysis | 73.2 | 75.7 | 78.2 |
Performance by hardware and tool
Every hardware/tool/quantization combination qwen3.8-35b-miniplus 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 |
|---|---|---|---|---|---|---|---|---|
| NVIDIA RTX A2000 12GB | llama.cpp | — | 78.2 tok/s | 77.9 tok/s | 21.7 GB | 65,536 tokens | 73.7 | 2 |
Benchmark runs
All 2 qwen3.8-35b-miniplus runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is qwen3.8-35b-miniplus good for coding?
- In our benchmarks, qwen3.8-35b-miniplus scores 70.9/100 for coding. It runs at about 77.9 tok/s, so if you want more speed, Nex-N2.5-mini-IQ3_XXS is faster (~91.4 tok/s) and still scores well for coding (81.6/100).
- Is qwen3.8-35b-miniplus good for agentic (tool-using) tasks?
- In our benchmarks, qwen3.8-35b-miniplus scores 77.8/100 for agentic workflows. It runs at about 77.9 tok/s, so if you want more speed, qwen3.8-flash-next-iq3_s is faster (~116.8 tok/s) and still scores well for agentic workflows (88.4/100).
- How fast is qwen3.8-35b-miniplus for local inference?
- Across 2 community benchmark runs, qwen3.8-35b-miniplus reaches up to 78.2 tok/s and averages 77.9 tok/s, with the fastest results on NVIDIA RTX A2000 12GB.
- How much memory does qwen3.8-35b-miniplus need?
- The leanest observed configuration used about 21.7 GB of memory.
- Which tools have been used to run qwen3.8-35b-miniplus?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.