qwen2.5 coder 14b bitnet 1.58b needs about 8.6 GB of memory at its main file (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Experimental BitNet 1.58‑bit Qwen2.5‑Coder 14B for code tasks
This model is a BitNet 1.58‑bit ternary quantization of Qwen2.5‑Coder‑14B‑Instruct. It contains 14.7B parameters stored as packed ternary values and is released under Apache 2.0. The GGUF file is 6.53 GB and requires a custom runtime.
Good at
- coding
- tools
- code generation
Limits
- context limited to 32,768 tokens
- experimental quality not benchmarked
- requires custom runtime
Best for
- code generation
- debugging assistance
- code reasoning
Who it’s for. Developers and researchers who need a lightweight, code‑focused LLM and are willing to evaluate an experimental quantized model. The model is suitable for prototyping and research rather than production deployments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 6.5 GB | 8.6 GB | Too big | Get file → |
The only available quant is unknown, 6.53 GB. It estimates 8.6 GB of VRAM at 8 k context, so it will not run on 8 GB VRAM. For 16 GB VRAM or higher, it is feasible. Use the provided GGUF file with llama.cpp or compatible runtimes.
What GPU do you need for qwen2.5 coder 14b bitnet 1.58b?
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: the best quant that fits is the main file (6.5 GB file, about 8.6 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about qwen2.5 coder 14b bitnet 1.58b
How much VRAM does qwen2.5 coder 14b bitnet 1.58b need?
About 8.6 GB at its main file with an 8K context window. That is the 6.5 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 bitnet 1.58b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of qwen2.5 coder 14b bitnet 1.58b GGUF?
It depends on the quant: file is 6.5 GB.
What context length does qwen2.5 coder 14b bitnet 1.58b 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 bitnet 1.58b GGUF?
The files are on Hugging Face in the tzervas/qwen2.5-coder-14b-bitnet-1.58b 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 bitnet 1.58b 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 this model on 8 GB VRAM?
The GGUF file is 6.53 GB and requires about 8.6 GB of VRAM at 8 k context, so 8 GB VRAM is insufficient.
Is this model ready for production use?
No, the model is experimental and its quality has not been benchmarked. It is intended for research and evaluation.
What is the maximum context length?
The model was trained with a context of 32,768 tokens.