QW

Qwen2.5 Coder 32B

QwenGGUF by lmstudio-communityUpdated 2024-11-11
Download on Hugging Face
Parameters32.8B
Context32K
Layers64
Architectureqwen2
Smallest quant17.2 GB
Quick answer

Qwen2.5 Coder 32B needs about 22.5 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 17.2 GB (Q3_K_L) to 34.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

32B Qwen2.5 Coder – large‑scale code generation model

Qwen2.5 Coder 32B is a 32.5 billion‑parameter causal language model optimized for code generation, reasoning, and fixing. It supports a maximum context length of 128 k tokens and is trained on 5.5 trillion source‑code tokens.

Good at

  • Code generation
  • Code reasoning
  • Code fixing

Limits

  • No vision support
  • Not intended for conversational use
  • Requires large VRAM for full precision

Best for

  • Automated code completion
  • Complex code debugging
  • Large‑scale code analysis

Who it’s for. Developers and researchers needing high‑quality code generation in a non‑chatting setting. The model is best used for completion and generation tasks, not for interactive dialogue.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L17.2 GB 19.9 GB
Too big Get file →
Q4_K_M19.9 GB 22.5 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →
Q8_034.8 GB 37.5 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_L (17.25 GB file, ~20 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (19.85 GB file, ~22.5 GB memory). For 16 GB VRAM, Q6_K (26.89 GB file, ~29.5 GB memory). Full precision Q8_0 requires ~35 GB file and ~37.5 GB memory.

What GPU do you need for Qwen2.5 Coder 32B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (19.9 GB file, about 22.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (34.8 GB file, about 37.5 GB in use).

Which Qwen2.5 Coder 32B quant should you choose?

Q4_K_M is the usual starting point for Qwen2.5 Coder 32B: it balances file size and quality well. Here it is a 19.9 GB file.

The Q8_0 file is 34.8 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_L at 17.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters32.8B
Layers64
Trained context32,768 tokens
KV cache (fp16)256 KB per token

Source

Quantized bylmstudio-community
FamilyQwen
Licenseapache-2.0
Downloads (HF)7,774
Last updated2024-11-11

Frequently asked questions about Qwen2.5 Coder 32B

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

About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Qwen2.5 Coder 32B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen2.5 Coder 32B GGUF?

It depends on the quant: Q3_K_L is 17.2 GB, Q4_K_M is 19.9 GB, Q6_K is 26.9 GB, Q8_0 is 34.8 GB.

What context length does Qwen2.5 Coder 32B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Qwen2.5 Coder 32B GGUF?

The files are on Hugging Face in the lmstudio-community/Qwen2.5-Coder-32B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Qwen2.5 Coder 32B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Qwen2.5 Coder 32B on 8 GB VRAM?

Use the Q3_K_L quantization; it requires about 20 GB of VRAM at 8 k context, so 8 GB is insufficient.

Does this model support image input?

No, the model has no vision capabilities.

Is the model suitable for chat applications?

No, it is intended for completion and generation, not conversational use.

Other GGUFs of Qwen2.5-Coder-32B

Similar models

Browse all →

More from lmstudio-community

All by lmstudio-community →

More Qwen models

All Qwen →

Other medium models

All medium models →