Can Qwen3.5 35B A3B run on the RTX 3070?
Not fully in VRAM. Even at 2-bit with 8K context, Qwen3.5 35B A3B needs about 13.6 GB, more than the 7.6 GB usable on the RTX 3070. It can still run with offload (slower): Q4_K_M with part of the model in system RAM, about 34–56 tokens/sec (estimate). Details and command.
Runs with offload (slower)
Runs with offload 4-bit (Q4_K_M) at 8K context: all attention layers plus the experts of 8 of 40 MoE layers on the RTX 3070 (about 6.0 GB), and the experts of the other 32 layers in system RAM (about 14.7 GB). Needs a PC with at least 32 GB of system RAM. Estimated speed: 34–56 tokens/sec (usable for chat), versus a bandwidth ceiling of ~244 tok/s if it fit fully in VRAM.
llama-server -hf unsloth/Qwen3.5-35B-A3B-GGUF:Q4_K_M -c 8192 -ngl 999 --n-cpu-moe 32
Estimate, not a benchmark. The command downloads the GGUF from Hugging Face. The speed range spans dual-channel DDR4-3200 to DDR5-6000 system RAM; your CPU, RAM speed and llama.cpp version move it. If llama.cpp runs out of GPU memory, raise --n-cpu-moe by 1-2; if VRAM is left over, lower it for more speed. Recent llama.cpp builds can also pick the split automatically. How we estimate offload.
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) • | 16.2 GB No | 16.3 GB No | 16.7 GB No | 18.6 GB No | — |
| 4-bit (Q4_K_M) • | 21.5 GB No | 21.5 GB No | 22.0 GB No | 23.9 GB No | — |
| 5-bit (Q5_K_M) • | 25.4 GB No | 25.5 GB No | 25.9 GB No | 27.8 GB No | — |
| 6-bit (Q6_K) • | 27.8 GB No | 27.9 GB No | 28.4 GB No | 30.2 GB No | — |
| 8-bit (Q8_0) • | 35.3 GB No | 35.4 GB No | 35.9 GB No | 37.7 GB No | — |
| 16-bit (F16/BF16) • | 65.6 GB No | 65.6 GB No | 66.1 GB No | 68.0 GB No | — |
• real GGUF file size from unsloth/Qwen3.5-35B-A3B-GGUF. Speed is a bandwidth ceiling (448 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
What fits instead
- Cheapest listed GPU that runs Qwen3.5 35B A3B: RTX 5090 (32 GB, launch MSRP $1,999) at Q5_K_M, fully in VRAM at 8K context.
- Largest popular model that fits the RTX 3070: Qwen3.5 9B (9.7B) at Q4_K_M, about 6.4 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
Qwen3.5 35B A3B on every GPU and Mac · Every model that runs on the RTX 3070 · Other models that fit 8 GB VRAM · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (Qwen/Qwen3.5-35B-A3B), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.