Question 1

Can I run Qwen3.5 35B A3B on a AMD Radeon RX 7900 XTX?

Accepted Answer

Yes — AMD Radeon RX 7900 XTX runs Qwen3.5 35B A3B fully on GPU at the Q4_K_M quantization. Full GPU inference — 24 GB VRAM meets the 22.8 GB recommendation.

Question 2

What quantization of Qwen3.5 35B A3B should I use on a AMD Radeon RX 7900 XTX?

Accepted Answer

For 24 GB VRAM on the AMD Radeon RX 7900 XTX, the Q4_K_M variant is the best fit. Estimated ~43.9 tokens/sec on the Q4_K_M quantization.

Question 3

How fast does Qwen3.5 35B A3B run on AMD Radeon RX 7900 XTX?

Accepted Answer

Roughly 43.9 tokens/sec for Q4_K_M. Real speed depends on context length, backend (Ollama, llama.cpp, LM Studio), and KV cache size.

Question 4

What if AMD Radeon RX 7900 XTX is not enough for Qwen3.5 35B A3B?

Accepted Answer

Try a smaller quantization variant or run on CPU + RAM with the trade-off of slower generation.

Quantization	File Size	Min VRAM	Rec VRAM	Context	Verdict	Estimated tok/s
Q4_K_MBest fit	17.5 GB	20.1 GB	22.8 GB	8K / 8K	Full GPU	~43.9
Q5_K_M	21.9 GB	25.2 GB	28.5 GB	8K / 8K	Hybrid CPU+GPU	~12
Q8_0	35 GB	40.3 GB	45.5 GB	8K / 8K	Hybrid CPU+GPU	~8
FP16	70 GB	80.5 GB	91 GB	8K / 8K	Can't Run	—

Can I Run Qwen3.5 35B A3B on AMD Radeon RX 7900 XTX?

Share this matchup

Every Qwen3.5 35B A3B quantization on AMD Radeon RX 7900 XTX