Model benchmarks
qwen36-35b_VISION local LLM performance
As of August 2026, qwen36-35b_VISION runs at up to 33.9 tok/s for local inference (best of 4 community benchmark runs across 1 GPU).
LM Studio
Model size
35B
Peak speed
33.9 tok/s
Average speed
33.7 tok/s
Min memory
17.1 GB
Max context
4,379 tokens
Best quality
86.4
Benchmark runs
4
GPUs tested
1
Performance by hardware and tool
Every hardware/tool/quantization combination qwen36-35b_VISION has been benchmarked on, ranked by peak token generation speed. Last updated August 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 3080 | LM Studio | — | 33.9 tok/s | 33.7 tok/s | 17.1 GB | 4,379 tokens | 65.1 | 4 |
Frequently asked questions
- How fast is qwen36-35b_VISION for local inference?
- Across 4 community benchmark runs, qwen36-35b_VISION reaches up to 33.9 tok/s and averages 33.7 tok/s, with the fastest results on NVIDIA GeForce RTX 3080.
- How much memory does qwen36-35b_VISION need?
- The leanest observed configuration used about 17.1 GB of memory.
- Which tools have been used to run qwen36-35b_VISION?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.