PH

Phi 3 Medium 4k Instruct

PhiGGUF by bartowskiUpdated 2024-08-09
Download on Hugging Face
Parameters14B
Context4K
Layers40
Architecturephi3
Smallest quant4.7 GB
Quick answer

Phi 3 Medium 4k Instruct needs about 10.7 GB of memory at Q4_K_M (a 8.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 20 quants, from 4.7 GB (IQ2_M) to 55.8 GB (F32).

Phi 3 Medium 4k Instruct – 14B parameter model for instruction following

Phi 3 Medium 4k Instruct is a 14B parameter model trained on Phi-3 datasets. It supports a 4096 token context length and is optimized for coding, math, and logical reasoning. The model is released under the MIT license and is available in multiple GGUF quantizations.

Good at

  • Coding and code generation
  • Mathematical reasoning
  • Logical problem solving

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • MIT license only for non-commercial use

Best for

  • Developers building low‑latency instruction models
  • Researchers testing reasoning capabilities
  • Embedded AI applications with limited VRAM

Who it’s for. The model is suited for developers and researchers who need a compact, instruction‑following LLM with strong reasoning abilities. It is ideal for environments with limited GPU memory and for applications that require fast inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M4.7 GB 6.1 GB
Fits Get file →
Q2_K5.1 GB 6.5 GB
Fits Get file →
Q2_K_L5.3 GB 6.6 GB
Fits Get file →
IQ3_XS5.8 GB 7.1 GB
Fits Get file →
Q3_K_S6.1 GB 7.4 GB
Tight Get file →
IQ3_M6.5 GB 7.8 GB
Tight Get file →
Q3_K_M6.9 GB 8.3 GB
Too big Get file →
IQ4_XS7.5 GB 8.8 GB
Too big Get file →
Q3_K_L7.5 GB 8.8 GB
Too big Get file →
Q3_K_XL7.6 GB 9.0 GB
Too big Get file →
Q4_K_S8.0 GB 9.3 GB
Too big Get file →
Q4_K_M8.6 GB 9.9 GB
Too big Get file →
Q4_K_L8.7 GB 10.0 GB
Too big Get file →
Q5_K_S9.6 GB 11.0 GB
Too big Get file →
Q5_K_M10.1 GB 11.4 GB
Too big Get file →
Q5_K_L10.2 GB 11.5 GB
Too big Get file →
Q6_K11.5 GB 12.8 GB
Too big Get file →
Q6_K_L11.5 GB 12.9 GB
Too big Get file →
Q8_014.8 GB 16.2 GB
Too big Get file →
F3255.8 GB (2 parts) 57.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 7.95 GB, ~10.1 GB memory at 8k context). For 12 GB VRAM, Q4_K_M (8.57 GB, ~10.7 GB memory) is a good balance. If you have 16 GB VRAM, Q4_K_L (8.69 GB, ~10.9 GB memory) offers higher quality with acceptable memory usage.

What GPU do you need for Phi 3 Medium 4k Instruct?

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: the best quant that fits is IQ3_XS (5.8 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_S (9.6 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K_L (11.5 GB file, about 13.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.8 GB file, about 17.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (14.8 GB file, about 17.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (14.8 GB file, about 17.0 GB in use).

Which Phi 3 Medium 4k Instruct quant should you choose?

Q4_K_M is the usual starting point for Phi 3 Medium 4k Instruct: it balances file size and quality well. Here it is a 8.6 GB file.

The Q8_0 file is 14.8 GB, about 1.7 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 IQ2_M at 4.7 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

Architecturephi3
Parameters14B
Layers40
Trained context4,096 tokens
KV cache (fp16)200 KB per token

Source

Quantized bybartowski
FamilyPhi
Licensemit
Downloads (HF)4,558
Last updated2024-08-09

Frequently asked questions about Phi 3 Medium 4k Instruct

How much VRAM does Phi 3 Medium 4k Instruct need?

About 10.7 GB at Q4_K_M with an 8K context window. That is the 8.6 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 3 Medium 4k Instruct on an 8 GB GPU?

Yes, with IQ3_XS: 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 3 Medium 4k Instruct GGUF?

It depends on the quant: IQ2_M is 4.7 GB, Q2_K is 5.1 GB, Q2_K_L is 5.3 GB, IQ3_XS is 5.8 GB, Q3_K_S is 6.1 GB, IQ3_M is 6.5 GB and 14 more.

What context length does Phi 3 Medium 4k Instruct support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.7 GB at 8K and 0.8 GB at 4K.

Where can I download Phi 3 Medium 4k Instruct GGUF?

The files are on Hugging Face in the bartowski/Phi-3-medium-4k-instruct-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 3 Medium 4k Instruct 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 3 Medium 4k Instruct on 8 GB VRAM?

Yes, using the Q4_K_S quantization which requires about 10.1 GB of VRAM at 8k context, slightly above 8 GB but may fit with memory optimizations.

Does the model support image inputs?

No, Phi 3 Medium 4k Instruct does not include vision capabilities.

What license applies to this model?

The model is released under the MIT license, allowing free use with attribution.

Other GGUFs of Phi-3-medium-4k-instruct

Similar models

Browse all →

More from bartowski

All by bartowski →

More Phi models

All Phi →

Other medium models

All medium models →