VRAMfit guide · updated 2026-06-28

What GPU runs qwen3.5?

In short: qwen3.5 ships in several sizes, and VRAM scales with the size you pick. At Q4_K_M the small distills run on a single 8-16 GB card, while the full 122B build needs about 70 GB - workstation or multi-GPU territory. Pick the largest size that fits your card comfortably.

How much VRAM does qwen3.5 need?

Per size at a 8,192-token context. The last column is the smallest RETAIL card that runs that size comfortably at Q4_K_M (datacenter and Mac options excluded):

ModelParamsQ4_K_M VRAMQ8_0 VRAMSmallest comfortable retail GPU
qwen3.5:0.8b0.8B2.3 GB2.7 GBNVIDIA GeForce GTX 1650
qwen3.5:2b2B3.0 GB3.9 GBNVIDIA GeForce GTX 1650
qwen3.5:4b4B4.1 GB5.9 GBNVIDIA GeForce RTX 2060
qwen3.5:9b9B6.9 GB10.9 GBNVIDIA GeForce RTX 3080
qwen3.5:27b27B17.1 GB28.9 GBNVIDIA GeForce RTX 4090
qwen3.5:35b35B21.6 GB36.9 GBNVIDIA GeForce RTX 5090
qwen3.5:122b122B70.5 GB123.9 GBNVIDIA RTX PRO 6000 Blackwell

Which size should you run?

The distilled small sizes are the practical local picks - they fit common cards and stay fast. Larger sizes raise quality but quickly exceed a single consumer card, so match the size to your VRAM rather than always reaching for the biggest.

The card to run it on

For a strong, all-in-VRAM experience the NVIDIA RTX PRO 6000 Blackwell runs qwen3.5:122b comfortably at about 14 tok/s (estimated) at Q4_K_M. Check any other size on the fit board.

Frequently asked questions

How much VRAM does qwen3.5 need?

It depends on the size. The small distills fit 8-16 GB cards at Q4_K_M; the full 122B build needs about 70 GB - see the per-size table above.

Can I run qwen3.5 on a 24 GB GPU?

Yes for the small and mid sizes at Q4_K_M; the largest size overflows 24 GB and needs offloading or a bigger card.

Does a higher quant need a bigger card?

Yes - Q8_0 roughly doubles the weight memory versus Q4_K_M, so it can push a size up into the next card tier.

Tool Check your own GPU on the fit board