PH

Phi 4 Reasoning Heretic

PhiGGUF by mradermacherUpdated 2026-02-01
Download on Hugging Face
Parameters14.7B
Context32K
Layers40
Architecturephi3
Smallest quant0.0 GB
Quick answer

Phi 4 Reasoning 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). Longer context needs more: at 32K tokens the KV cache alone adds about 6.7 GB.

Phi 4 Reasoning Heretic – 14.7B Phi3 model for coding and reasoning

Phi 4 Reasoning Heretic is a 14.7B parameter Phi3 model optimized for coding and reasoning tasks. It supports up to 32768 context tokens and is released under the MIT license. The model is available in multiple GGUF quantizations.

Good at

  • Coding tasks
  • Reasoning problems
  • Long context handling

Limits

  • No vision support
  • Requires temperature=0.8, top_k=50, top_p=0.95, do_sample=True
  • Max new tokens 32768 for full CoT

Best for

  • Competitive coding contests
  • Math olympiad problem solving
  • Complex science Q&A

Who it’s for. Developers and researchers needing a large Phi model for code generation and reasoning. The model is suitable for applications that can handle the required context length and inference settings.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.2 GB
Fits Get file →
IQ1_S3.3 GB 5.5 GB
Fits Get file →
IQ1_M3.6 GB 5.8 GB
Fits Get file →
IQ2_XXS4.1 GB 6.3 GB
Fits Get file →
IQ2_XS4.5 GB 6.7 GB
Fits Get file →
IQ2_S4.7 GB 6.9 GB
Fits Get file →
IQ2_M5.1 GB 7.3 GB
Tight Get file →
Q2_K_S5.2 GB 7.4 GB
Tight Get file →
Q2_K5.5 GB 7.7 GB
Tight Get file →
IQ3_XXS5.8 GB 8.0 GB
Too big Get file →
IQ3_XS6.2 GB 8.4 GB
Too big Get file →
IQ3_S6.5 GB 8.7 GB
Too big Get file →
Q3_K_S6.5 GB 8.7 GB
Too big Get file →
IQ3_M6.9 GB 9.1 GB
Too big Get file →
Q3_K_M7.4 GB 9.5 GB
Too big Get file →
Q3_K_L7.9 GB 10.1 GB
Too big Get file →
IQ4_XS7.9 GB 10.1 GB
Too big Get file →
IQ4_NL8.4 GB 10.6 GB
Too big Get file →
Q4_08.4 GB 10.6 GB
Too big Get file →
Q4_K_S8.4 GB 10.6 GB
Too big Get file →
Q4_K_M9.1 GB 11.2 GB
Too big Get file →
Q4_19.3 GB 11.4 GB
Too big Get file →
Q5_K_S10.2 GB 12.3 GB
Too big Get file →
Q5_K_M10.6 GB 12.8 GB
Too big Get file →
Q6_K12.0 GB 14.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (3.32 GB, 5.5 GB memory at 8k context) or IQ1_M (3.6 GB, 5.8 GB). For 12 GB VRAM, Q4_K_M (9.05 GB, 11.2 GB) or Q5_K_M (10.6 GB, 12.8 GB) are suitable. Larger VRAM allows Q6_K (12.03 GB, 14.2 GB).

What GPU do you need for Phi 4 Reasoning 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 Reasoning Heretic quant should you choose?

Q4_K_M is the usual starting point for Phi 4 Reasoning 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

Architecturephi3
Parameters14.7B
Layers40
Trained context32,768 tokens
KV cache (fp16)200 KB per token

Source

Quantized bymradermacher
FamilyPhi
Licensemit
Downloads (HF)633
Last updated2026-02-01

Frequently asked questions about Phi 4 Reasoning Heretic

How much VRAM does Phi 4 Reasoning 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 Reasoning 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 Reasoning 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 Reasoning Heretic support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.7 GB at 32K.

Where can I download Phi 4 Reasoning Heretic GGUF?

The files are on Hugging Face in the mradermacher/Phi-4-reasoning-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 Reasoning 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 Reasoning Heretic on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations, which fit within 8 GB VRAM and use about 5.5–5.8 GB memory at 8k context.

What inference settings are required?

Set temperature=0.8, top_k=50, top_p=0.95, do_sample=True, and for long chain-of-thought set max_new_tokens=32768.

Is the model licensed for commercial use?

The model is released under the MIT license, allowing commercial use.

Other GGUFs of Phi-4-reasoning-heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Phi models

All Phi →

Other medium models

All medium models →