QW

Qwen2.5 Coder 32B Instruct AWQ

QwenGGUF by QwenUpdated 2025-01-12
Download on Hugging Face
Parameters32.8B
Context128K
Layers64
Architectureqwen2
Smallest quant24.6 GB
Quick answer

Qwen2.5 Coder 32B Instruct AWQ needs about 42.4 GB of memory at Q4_K_M (a 39.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 9 quants, from 24.6 GB (Q2_K) to 69.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Qwen2.5 Coder 32B Instruct AWQ – a 32.8B code‑focused LLM in GGUF format

Qwen2.5 Coder 32B Instruct AWQ is a 32.8B parameter model tuned for code generation and reasoning. It supports a full context length of 131,072 tokens and is available in multiple GGUF quantizations. The model is licensed under apache‑2.0.

Good at

  • Code generation
  • Code reasoning
  • Code fixing

Limits

  • No vision support
  • Requires 8‑K context for memory estimates
  • Large VRAM needed for higher quants

Best for

  • Developing code assistants
  • Automating code reviews
  • Generating complex code snippets

Who it’s for. Developers and researchers needing a large, open‑source code LLM with long‑context support. The model is suitable for projects that can allocate sufficient VRAM and use vLLM or llama.cpp for inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K24.6 GB (3 parts) 27.3 GB
Too big Get file →
Q3_K_M31.9 GB (3 parts) 34.5 GB
Too big Get file →
Q4_037.3 GB (4 parts) 39.9 GB
Too big Get file →
Q4_K_M39.7 GB (4 parts) 42.4 GB
Too big Get file →
Q5_045.3 GB (4 parts) 47.9 GB
Too big Get file →
Q5_K_M46.5 GB (4 parts) 49.2 GB
Too big Get file →
Q6_K53.8 GB (5 parts) 56.4 GB
Too big Get file →
—65.5 GB (9 parts) 68.2 GB
Too big Get file →
Q8_069.6 GB (6 parts) 72.3 GB
Too big Get file →

For 8‑GB VRAM, use Q2_K (24.63 GB file, ~27.3 GB memory at 8K context). For 16‑GB VRAM, Q3_K_M (31.87 GB file, ~34.5 GB memory) or Q4_0 (37.28 GB file, ~39.9 GB memory). Higher quants such as Q5_0 or Q6_K require more than 32 GB VRAM.

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

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q2_K (24.6 GB file, about 27.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_0 (45.3 GB file, about 47.9 GB in use).

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

Q4_K_M is the usual starting point for Qwen2.5 Coder 32B Instruct AWQ: it balances file size and quality well. Here it is a 39.7 GB file.

The Q8_0 file is 69.6 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 Q2_K at 24.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters32.8B
Layers64
Trained context131,072 tokens
KV cache (fp16)256 KB per token

Source

Quantized byQwen
FamilyQwen
Licenseapache-2.0
Downloads (HF)43,454
Last updated2025-01-12

Frequently asked questions about Qwen2.5 Coder 32B Instruct AWQ

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

About 42.4 GB at Q4_K_M with an 8K context window. That is the 39.7 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 Instruct AWQ on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 27.3 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q2_K is 24.6 GB, Q3_K_M is 31.9 GB, Q4_0 is 37.3 GB, Q4_K_M is 39.7 GB, Q5_0 is 45.3 GB, Q5_K_M is 46.5 GB and 3 more.

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

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Instruct AWQ GGUF?

The files are on Hugging Face in the Qwen/Qwen2.5-Coder-32B-Instruct-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 Instruct AWQ 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 Instruct AWQ on 8 GB VRAM?

The Q2_K quant requires about 27.3 GB memory at 8K context, so 8 GB VRAM is insufficient. Use a smaller model or lower quantization if available.

Does this model support image inputs?

No, the model has no vision capabilities.

What is the maximum context length I can use?

The model supports up to 131,072 tokens, but only vLLM supports YARN for length extrapolation.

Other GGUFs of Qwen2.5-Coder-32B-Instruct

Similar models

Browse all →

More from Qwen

All by Qwen →

More Qwen models

All Qwen →

Other medium models

All medium models →