PXA Coder needs about 20.2 GB of memory at its main file (a 19.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.
PXA Coder 35B – a large coding model for developers
PXA Coder is a 34.7B parameter model built on the qwen35moe architecture. It is designed for coding, reasoning, tools, and vision tasks. The model is released under the Apache-2.0 license.
Good at
- Coding
- Reasoning
- Vision
Limits
- Requires custom engine, not compatible with llama.cpp, LM Studio, ollama, or text-generation-webui
- Large memory footprint, 20.2 GB at 8 k context
- No stock support for standard GGUF engines
Best for
- Developers needing advanced code generation
- Complex reasoning tasks
- Vision‑enabled coding workflows
Who it’s for. This model is intended for developers and researchers who need a powerful coding assistant and are willing to use the dedicated PXA engine. It is not suitable for users who require out‑of‑the‑box compatibility with common LLM frameworks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 19.0 GB | 20.2 GB | Too big | Get file → |
The only available quant is 19 GB. It requires roughly 20.2 GB of VRAM at 8 k context, so a 24 GB GPU is recommended. Memory estimates are approximate.
What GPU do you need for PXA Coder?
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 the main file (19.0 GB file, about 20.2 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about PXA Coder
How much VRAM does PXA Coder need?
About 20.2 GB at its main file with an 8K context window. That is the 19.0 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 PXA Coder on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of PXA Coder GGUF?
It depends on the quant: file is 19.0 GB.
What context length does PXA Coder support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.
Where can I download PXA Coder GGUF?
The files are on Hugging Face in the poisonxa/PXA-Coder-35B-PXQ4 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does PXA Coder 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 PXA Coder on 8 GB VRAM?
No, the model requires about 20.2 GB of VRAM at 8 k context.
Does PXA Coder support vision?
Yes, it has detected vision capabilities.