QW

Qwen2.5 Coder 14B Instruct

QwenGGUF by apto-asUpdated 2024-11-24
Download on Hugging Face
Parameters14.8B
Context32K
Layers48
Architectureqwen2
Smallest quant10.5 GB
Quick answer

Qwen2.5 Coder 14B Instruct needs about 12.6 GB of memory at Q5_K_M (a 10.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Qwen2.5 Coder 14B Instruct – a code‑focused large language model

Qwen2.5 Coder 14B Instruct is a 14.8‑billion‑parameter transformer trained on 5.5 trillion tokens of source code and text. It supports instruction following and long‑context processing up to 131,072 tokens. The model is released under the apache‑2.0 license.

Good at

  • Code generation
  • Code reasoning
  • Tool usage

Limits

  • No vision support
  • Requires 12.6 GB VRAM at 8 k context
  • Large context length may need special handling

Best for

  • Developing code assistants
  • Automating code fixes
  • Generating code snippets

Who it’s for. Developers and researchers needing a large, open‑source code‑LLM for instruction‑driven tasks. The model is suitable for projects that can allocate sufficient GPU memory and handle long‑context inputs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M10.5 GB 12.6 GB
Too big Get file →

The available Q5_K_M quantization has a file size of 10.51 GB and requires about 12.6 GB of VRAM at 8 k context. For GPUs with 12 GB or more, this quant is recommended. Smaller VRAM budgets would need a different quantization not provided here.

What GPU do you need for Qwen2.5 Coder 14B Instruct?

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: the best quant that fits is Q5_K_M (10.5 GB file, about 12.6 GB in use).

Which Qwen2.5 Coder 14B Instruct quant should you choose?

Q5_K_M (10.5 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters14.8B
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized byapto-as
FamilyQwen
Licenseapache-2.0
Downloads (HF)783
Last updated2024-11-24

Frequently asked questions about Qwen2.5 Coder 14B Instruct

How much VRAM does Qwen2.5 Coder 14B Instruct need?

About 12.6 GB at Q5_K_M with an 8K context window. That is the 10.5 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 14B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen2.5 Coder 14B Instruct GGUF?

It depends on the quant: Q5_K_M is 10.5 GB.

What context length does Qwen2.5 Coder 14B Instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Qwen2.5 Coder 14B Instruct GGUF?

The files are on Hugging Face in the apto-as/Qwen2.5-Coder-14B-Instruct-Q5_K_M-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 14B Instruct 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 14B Instruct on 8 GB VRAM?

No. The Q5_K_M quant requires approximately 12.6 GB of VRAM at 8 k context, which exceeds an 8 GB GPU.

Does this model support long‑context inference?

Yes. The model supports a full context length of 131,072 tokens, though handling very long inputs may need techniques like YaRN.

Can I use this model with vLLM?

Yes. The model is compatible with vLLM for efficient deployment.

Other GGUFs of Qwen2.5-Coder-14B-Instruct

Similar models

Browse all →

More from apto-as

All by apto-as →

More Qwen models

All Qwen →

Other medium models

All medium models →