Skip to content
localmodel.run

Model family · 3 sizes

Qwen3.6: which size runs locally?

Qwen3.6 comes in 3 sizes, from 27.8B to 36B. Some sizes are Mixture-of-Experts, so they run faster than their memory footprint suggests. Here is each size with its Q4_K_M weight, the memory it needs, and the hardware that runs it.

Sizes
3
Smallest
27.8B
Largest
36B
Runs from
24GB

The Qwen3.6 lineup

Smallest first Q4_K_M · min memory

"Needs" is the sourced minimum memory for Q4_K_M with a small context. Larger context needs more.

Which Qwen3.6 fits your memory

8GB

No Qwen3.6 size fits 8GB; even Qwen3.6 27B needs more.

No
16GB

No Qwen3.6 size fits 16GB; even Qwen3.6 27B needs more.

No
24GB

Largest that fits: Qwen3.6 27B (27.8B), best case on Nvidia GeForce RTX 4090 (24GB).

Yes
32GB

Largest that fits: Qwen3.6 35B-A3B (36B), best case on Nvidia GeForce RTX 5090 (32GB).

Yes
48GB

Largest that fits: Qwen3.6 35B-A3B (36B), best case on Apple M5 Pro (48GB).

Yes
64GB

Largest that fits: Qwen3.6 35B-A3B (36B), best case on Apple M4 Max (64GB).

Yes
128GB

Largest that fits: Qwen3.6 35B-A3B (36B), best case on Apple M5 Max (128GB).

Yes
256GB

Largest that fits: Qwen3.6 35B-A3B (36B), best case on Apple M3 Ultra (256GB).

Yes

Best case means the most capable device at that size (usually a discrete GPU). A Mac at the same size sits roughly one rung lower; see the per-size breakdown on each memory budget page.

FAQ

Which Qwen3.6 size should I run locally?

Pick the largest size your memory allows. On 24GB (best case) up to Qwen3.6 27B; On 32GB (best case) up to Qwen3.6 35B-A3B; On 48GB (best case) up to Qwen3.6 35B-A3B; On 64GB (best case) up to Qwen3.6 35B-A3B; On 128GB (best case) up to Qwen3.6 35B-A3B; On 256GB (best case) up to Qwen3.6 35B-A3B. Smaller sizes run faster and leave headroom for context.

What is the smallest Qwen3.6 model?

Qwen3.6 27B at 27.8B parameters, about 16.82 GB on disk at Q4_K_M. It is the one to use on phones and 8 GB machines.

What is the largest Qwen3.6 model and what does it need?

Qwen3.6 35B-A3B at 36B (mixture of experts), about 22.29 GB at Q4_K_M. It fits a high-memory desktop GPU or Mac.

Understand the numbers

Short guides to the ideas behind Qwen3.6's memory and quant figures.

Sources

Memory figures are estimates at Q4_K_M. See methodology.