Qwen2.5 Coder 32B VRAM and GPU Requirements

Qwen2.5 Coder 32B needs about 20.16 GB at Q4_K_M with 8K context.

Which GPUs fit

VRAM by quantization

Totals at 8,192 tokens. Q4_K_M is the usual balance of size and quality. FP16 weights are the parameter count times 2 bytes. The FP16 column in the table is the full estimate: weights, cache, and 1 GB.

Context length

Q4_K_M total as the context changes. Cache is the part that grows.

• 2,048 18.66 GB
• 8,192 20.16 GB
• 32,768 26.16 GB

Qwen2.5 Coder 32B hardware notes

• Unified memory counts 75 percent of the listed pool as usable. Discrete cards use the full listed memory. The memory column still shows the listed figure.
• Last updated 2025-01-12.
• Weights, cache, and the 1 GB overhead are estimates. How this is calculated.
• Architecture numbers and the parameter count come from the public model record, checked 2026-10-10.

Qwen2.5 Coder 32B VRAM FAQ

How much VRAM does Qwen2.5 Coder 32B need at Q4_K_M?

20.16 GB at 8,192 tokens. Weights are 17.16 GB, the cache is 2.00 GB, and overhead is 1 GB.

Does a 24 GB GPU fit Qwen2.5 Coder 32B at Q4_K_M?

GeForce RTX 3090 24GB is Fits, 3.84 GB left. The quant table uses 8,192 tokens, the smaller of 8,192 and the configured maximum of 32,768.

What context length is configured for Qwen2.5 Coder 32B?

The configured context length is 32,768 tokens. The quant table uses 8,192 tokens, the smaller of 8,192 and the configured maximum of 32,768.

Which source supplies the parameter count for Qwen2.5 Coder 32B?

32.76B parameters, from the Hugging Face model record for Qwen/Qwen2.5-Coder-32B-Instruct.

Related models