Can Qwen3.6 35B A3B run on the RTX 4060?
No. Even at 2-bit with 8K context, Qwen3.6 35B A3B needs about 13.6 GB, more than the 7.6 GB usable on the RTX 4060.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 13.5 GB No | 13.6 GB No | 14.1 GB No | 15.9 GB No | — |
| 3-bit (Q3_K_M) • | 16.9 GB No | 17.0 GB No | 17.4 GB No | 19.3 GB No | — |
| 4-bit (Q4_K_M) • | 22.1 GB No | 22.1 GB No | 22.6 GB No | 24.5 GB No | — |
| 5-bit (Q5_K_M) • | 26.2 GB No | 26.3 GB No | 26.7 GB No | 28.6 GB No | — |
| 6-bit (Q6_K) • | 28.9 GB No | 29.0 GB No | 29.4 GB No | 31.3 GB No | — |
| 8-bit (Q8_0) • | 36.2 GB No | 36.2 GB No | 36.7 GB No | 38.6 GB No | — |
| 16-bit (F16/BF16) • | 67.1 GB No | 67.2 GB No | 67.7 GB No | 69.6 GB No | — |
• real GGUF file size from unsloth/Qwen3.6-35B-A3B-MTP-GGUF. Speed is a bandwidth ceiling (272 GB/s), not a benchmark. Methodology.
Hardware that does fit it
RTX 4060 Ti 16GBRTX 4070 Ti SuperRTX 4080RTX 4080 SuperRTX 5060 Ti 16GBRTX 5070 Ti
More
Qwen3.6 35B A3B on every GPU and Mac · Every model that runs on the RTX 4060 · Other models that fit 8 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (Qwen/Qwen3.6-35B-A3B), NVIDIA specs. Data as of 2026-11-17.