Phi 4 Heretic needs about 11.2 GB of memory at Q4_K_M (a 9.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 12.0 GB (Q6_K).
Phi 4 Heretic – 14.7B param LLM for coding
Phi 4 Heretic is a 14.7B parameter model based on the phi3 architecture. It is trained on a diverse dataset including code, educational content, and synthetic textbook data. The model is released under the MIT license.
Good at
- Coding
- Educational content
- General reasoning
Limits
- No vision support
- Limited language coverage
- Requires large VRAM for higher quants
Best for
- Code generation
- Educational tutoring
- Research prototyping
Who it’s for. Developers and researchers who need a large language model focused on coding and educational content. The model is suitable for local deployment with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.2 GB | Fits | Get file → | |
| IQ1_S | 3.3 GB | 5.5 GB | Fits | Get file → | |
| IQ1_M | 3.6 GB | 5.8 GB | Fits | Get file → | |
| IQ2_XXS | 4.1 GB | 6.3 GB | Fits | Get file → | |
| IQ2_XS | 4.5 GB | 6.7 GB | Fits | Get file → | |
| IQ2_S | 4.7 GB | 6.9 GB | Fits | Get file → | |
| IQ2_M | 5.1 GB | 7.3 GB | Tight | Get file → | |
| Q2_K_S | 5.2 GB | 7.4 GB | Tight | Get file → | |
| Q2_K | 5.5 GB | 7.7 GB | Tight | Get file → | |
| IQ3_XXS | 5.8 GB | 8.0 GB | Too big | Get file → | |
| IQ3_XS | 6.2 GB | 8.4 GB | Too big | Get file → | |
| IQ3_S | 6.5 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_S | 6.5 GB | 8.7 GB | Too big | Get file → | |
| IQ3_M | 6.9 GB | 9.1 GB | Too big | Get file → | |
| Q3_K_M | 7.4 GB | 9.5 GB | Too big | Get file → | |
| Q3_K_L | 7.9 GB | 10.1 GB | Too big | Get file → | |
| IQ4_XS | 7.9 GB | 10.1 GB | Too big | Get file → | |
| IQ4_NL | 8.4 GB | 10.6 GB | Too big | Get file → | |
| Q4_0 | 8.4 GB | 10.6 GB | Too big | Get file → | |
| Q4_K_S | 8.4 GB | 10.6 GB | Too big | Get file → | |
| Q4_K_M | 9.1 GB | 11.2 GB | Too big | Get file → | |
| Q4_1 | 9.3 GB | 11.4 GB | Too big | Get file → | |
| Q5_K_S | 10.2 GB | 12.3 GB | Too big | Get file → | |
| Q5_K_M | 10.6 GB | 12.8 GB | Too big | Get file → | |
| Q6_K | 12.0 GB | 14.2 GB | Too big | Get file → |
For 8 GB VRAM use IQ1_S (3.32 GB) or IQ1_M (3.6 GB). For 12 GB VRAM use Q2_K (5.55 GB) or Q3_K_M (7.36 GB). For 16 GB VRAM use Q4_K_M (9.05 GB) or Q5_K_M (10.6 GB). Estimates are approximate.
What GPU do you need for Phi 4 Heretic?
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 the main file (0.0 GB file, about 2.2 GB in use).
- 6 GB VRAM: the best quant that fits is IQ1_M (3.6 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_XXS (5.8 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_1 (9.3 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.0 GB file, about 14.2 GB in use).
Which Phi 4 Heretic quant should you choose?
Q4_K_M is the usual starting point for Phi 4 Heretic: it balances file size and quality well. Here it is a 9.1 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Phi 4 Heretic
How much VRAM does Phi 4 Heretic need?
About 11.2 GB at Q4_K_M with an 8K context window. That is the 9.1 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 Phi 4 Heretic on an 8 GB GPU?
Yes, with IQ3_XXS: the 5.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Phi 4 Heretic GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 3.3 GB, IQ1_M is 3.6 GB, IQ2_XXS is 4.1 GB, IQ2_XS is 4.5 GB, IQ2_S is 4.7 GB and 19 more.
What context length does Phi 4 Heretic 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 Phi 4 Heretic GGUF?
The files are on Hugging Face in the mradermacher/phi-4-heretic-i1-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 Phi 4 Heretic 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 Phi 4 Heretic on 8 GB VRAM?
Yes, use the IQ1_S or IQ1_M quant, which are 3.32 GB and 3.6 GB respectively.
Does Phi 4 Heretic support vision tasks?
No, the model has no vision capabilities.