phi4 trader needs about 11.1 GB of memory at Q4_K_M (a 8.9 GB file) with an 8K context window, so it fits on a 12 GB GPU.
Phi4 Trader – 14.7B Llama‑style model fine‑tuned for trading
Phi4 Trader is a 14.7B parameter Llama architecture model fine‑tuned from unsloth/phi-4-unsloth-bnb-4bit. It supports a 16,384 token context window and is released under the apache‑2.0 license. The model is available in a single Q4_K_M quantized GGUF file.
Good at
- Financial text generation
- Trading strategy explanations
- Market data summarization
Limits
- No vision support
- Requires 8.89 GB GGUF file
- Context limited to 16,384 tokens
Best for
- Simulating trader conversations
- Generating trade reports
- Educating on market concepts
Who it’s for. Developers and researchers needing a lightweight, fine‑tuned trading LLM. The model is suitable for applications that require conversational finance content without heavy visual or multimodal inputs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 8.9 GB | 11.1 GB | Too big | Get file → |
The only available quant is Q4_K_M, 8.89 GB in size. It requires roughly 11.1 GB of VRAM at 8 k context, so a GPU with at least 12 GB VRAM is recommended. For systems with less memory, the model cannot be loaded in this quantization.
What GPU do you need for phi4 trader?
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 Q4_K_M (8.9 GB file, about 11.1 GB in use).
Which phi4 trader quant should you choose?
Q4_K_M is the usual starting point for phi4 trader: it balances file size and quality well. Here it is a 8.9 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about phi4 trader
How much VRAM does phi4 trader need?
About 11.1 GB at Q4_K_M with an 8K context window. That is the 8.9 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 phi4 trader on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of phi4 trader GGUF?
It depends on the quant: Q4_K_M is 8.9 GB.
What context length does phi4 trader support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.7 GB at 8K and 3.4 GB at 16K.
Where can I download phi4 trader GGUF?
The files are on Hugging Face in the Mazino0/phi4-trader repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does phi4 trader 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 Phi4 Trader on a GPU with 8 GB VRAM?
No. The Q4_K_M quant requires about 11.1 GB VRAM at 8 k context, exceeding 8 GB.
Is Phi4 Trader compatible with llama.cpp?
Yes, the GGUF file is compatible with llama.cpp for inference.
Does Phi4 Trader support vision or multimodal inputs?
No, the model only handles text and has no vision support.