Torchlight Phi4 Mini 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. This repository has 12 quants, from 1.7 GB (Q2_K) to 7.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Torchlight Phi4 Mini – a 3.8B Phi-3 model fine‑tuned for PyTorch questions
Torchlight Phi4 Mini is a 3.84B parameter Phi-3 model trained on 6,918 PyTorch forum chats. It focuses on coding and tool usage, providing concise answers and asking for missing details when needed.
Good at
- Coding queries
- Tool usage
- PyTorch troubleshooting
Limits
- No vision support
- Requires 8k context for full performance
- MIT license only
Best for
- Answering PyTorch forum questions
- Debugging code snippets
- Generating concise code fixes
Who it’s for. Developers and researchers needing quick, accurate PyTorch help. The model is suitable for local deployment on systems with limited VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.7 GB | 3.3 GB | Fits | Get file → | |
| Q3_K_S | 1.9 GB | 3.5 GB | Fits | Get file → | |
| Q3_K_M | 2.1 GB | 3.7 GB | Fits | Get file → | |
| IQ4_XS | 2.2 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_L | 2.3 GB | 3.9 GB | Fits | Get file → | |
| Q4_K_S | 2.3 GB | 3.9 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q5_K_S | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_M | 2.8 GB | 4.4 GB | Fits | Get file → | |
| Q6_K | 3.2 GB | 4.7 GB | Fits | Get file → | |
| Q8_0 | 4.1 GB | 5.7 GB | Fits | Get file → | |
| F16 | 7.7 GB | 9.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (2.49 GB file, ~4.1 GB memory). For 4 GB VRAM, use Q3_K_M (2.12 GB file, ~3.7 GB memory). If memory is very tight, Q2_K (1.73 GB file, ~3.3 GB memory) is the smallest option.
What GPU do you need for Torchlight Phi4 Mini?
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: the best quant that fits is Q4_K_S (2.3 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.7 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (7.7 GB file, about 9.3 GB in use).
Which Torchlight Phi4 Mini quant should you choose?
Q4_K_M is the usual starting point for Torchlight Phi4 Mini: it balances file size and quality well. Here it is a 2.5 GB file.
The Q8_0 file is 4.1 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 1.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Torchlight Phi4 Mini
How much VRAM does Torchlight Phi4 Mini 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 Torchlight Phi4 Mini on an 8 GB GPU?
Yes, with Q8_0: the 4.1 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Torchlight Phi4 Mini GGUF?
It depends on the quant: Q2_K is 1.7 GB, Q3_K_S is 1.9 GB, Q3_K_M is 2.1 GB, IQ4_XS is 2.2 GB, Q3_K_L is 2.3 GB, Q4_K_S is 2.3 GB and 6 more.
What context length does Torchlight Phi4 Mini 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 Torchlight Phi4 Mini GGUF?
The files are on Hugging Face in the mradermacher/torchlight-phi4-mini-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 Torchlight Phi4 Mini use?
Hugging Face lists the license as mit. 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 Torchlight Phi4 Mini on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 4.1 GB of VRAM at 8k context, which fits in 8 GB.
Does this model support image input?
No, Torchlight Phi4 Mini does not have vision capabilities.
What license does it use?
The model is released under the MIT license.