RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can Qwen3.6 35B A3B run on the RX 7900 XT?

Yes. At 8K context the best fit is Q3_K_M, using about 17.0 GB of the 19.0 GB usable on the RX 7900 XT. Estimated speed ceiling: ~560 tokens/sec.

Better quality with offload: 4-bit (Q4_K_M)

Runs with offload 4-bit (Q4_K_M) at 8K context: all attention layers plus the experts of 32 of 40 MoE layers on the RX 7900 XT (about 17.2 GB), and the experts of the other 8 layers in system RAM (about 3.7 GB). Needs a PC with at least 32 GB of system RAM. Estimated speed: 96–131 tokens/sec (usable for chat), versus a bandwidth ceiling of ~430 tok/s if it fit fully in VRAM.

llama-server -hf bartowski/Qwen_Qwen3.6-35B-A3B-GGUF:Q4_K_M -c 8192 -ngl 999 --n-cpu-moe 8 --no-mmproj

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.

+ 0.8 GB with image input. The figures on this page are for text only. With image input enabled, the vision projector (mmproj) file loads alongside the model: Q3_K_M at 8K context then needs about 17.8 GB (tight). llama.cpp's -hf downloads and loads it automatically unless you add --no-mmproj. Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •13.5 GB Fits13.6 GB Fits14.1 GB Fits16.0 GB Fits710
3-bit (Q3_K_M) •16.9 GB Fits17.0 GB Fits17.4 GB Tight19.3 GB No560
4-bit (Q4_K_M) •21.7 GB No21.8 GB No22.3 GB No24.1 GB No—
5-bit (Q5_K_M) •25.1 GB No25.2 GB No25.6 GB No27.5 GB No—
6-bit (Q6_K) •29.8 GB No29.9 GB No30.3 GB No32.2 GB No—
8-bit (Q8_0) •36.2 GB No36.2 GB No36.7 GB No38.6 GB No—
16-bit (F16/BF16) •67.1 GB No67.2 GB No67.7 GB No69.6 GB No—

• real GGUF file size from bartowski/Qwen_Qwen3.6-35B-A3B-GGUF. Speed is a bandwidth ceiling (800 GB/s), not a benchmark. Methodology.

What fits instead

"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

Qwen3.6 35B A3B on every GPU and Mac · Every model that runs on the RX 7900 XT · Other models that fit 24 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/Qwen3.6-35B-A3B), AMD specs. Model data last checked 2026-11-18; refreshed hourly.