community-verified · measured pool data
Can the Tesla V100 32GB run Qwen3.6-35B-A3B-GGUF?
Yes — community-measured at 58.3 tok/s (18 runs at 4-bit).
Verified single-stream runs on the Tesla V100 32GB from the localmaxxing public pool. Every number on this page is measured — nothing here is estimated.
| Quantization | Median tok/s | TTFT (ms) | Peak VRAM | Max context tested | Engines |
|---|---|---|---|---|---|
| 4-bit | 58.3 | 71447.3 | 21.5 GB | 262,144 | llama.cpp |