lexi coder v4.4 needs about 4.1 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Lexi Coder v4.4 – 3.84B Phi‑3 model for coding and tool use
Lexi Coder v4.4 is a 3.84B parameter Phi‑3 model fine‑tuned for coding tasks and tool integration. It builds on the previous Lexi Coder v4.3 and requires no PEFT adapters. The model is available in a single Q4_K_M quantized GGUF file.
Good at
- Writing maintainable code
- Explaining code decisions
- Integrating external tools
Limits
- No vision support
- Requires 8k context for full memory estimate
- License terms inherited from base model
Best for
- Developers needing code generation
- Tool‑centric workflows
- Educational coding assistants
Who it’s for. Developers and teams that need a lightweight, code‑focused LLM without vision capabilities. The model is suitable for local deployment and integration into coding tools.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.5 GB | 4.1 GB | Fits | Get file → |
The only available quant is Q4_K_M, file size 2.49 GB. It requires approximately 4.1 GB of VRAM at 8k context. For 8 GB VRAM, this quant is suitable; for larger models, consider higher‑bit quantizations if available.
What GPU do you need for lexi coder v4.4?
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: the best quant that fits is Q4_K_M (2.5 GB file, about 4.1 GB in use).
Which lexi coder v4.4 quant should you choose?
Q4_K_M is the usual starting point for lexi coder v4.4: it balances file size and quality well. Here it is a 2.5 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about lexi coder v4.4
How much VRAM does lexi coder v4.4 need?
About 4.1 GB at Q4_K_M with an 8K context window. That is the 2.5 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 lexi coder v4.4 on an 8 GB GPU?
Yes, with Q4_K_M: the 2.5 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of lexi coder v4.4 GGUF?
It depends on the quant: Q4_K_M is 2.5 GB.
What context length does lexi coder v4.4 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download lexi coder v4.4 GGUF?
The files are on Hugging Face in the reallexi/lexi-coder-v4.4 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does lexi coder v4.4 use?
Hugging Face lists the license as other. 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 Lexi Coder v4.4 on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 4.1 GB of VRAM at 8k context, leaving room for runtime overhead.
Does Lexi Coder v4.4 support image inputs?
No, the model has no vision capabilities.
Do I need a PEFT adapter to use this model?
No, the adapter is merged into the base weights, so no additional adapter is required.