PH

Phi 3 mini 128k instruct

PhiGGUF by mmngaUpdated 2024-04-24
Download on Hugging Face
Parameters3.82B
Context128K
Layers32
Architecturephi3
Smallest quant0.8 GB
Quick answer

Phi 3 mini 128k instruct needs about 6.1 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 0.8 GB (IQ1_S) to 4.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Phi 3 mini 128k instruct – 3.82 B parameter instruction‑tuned model

Phi 3 mini 128k instruct is a 3.82 B parameter model trained on 131072 context tokens. It is available in multiple GGUF quantizations and released under the MIT license. The model supports instruction following in a lightweight architecture.

Good at

  • Instruction following
  • Contextual reasoning up to 128k tokens
  • Low‑memory inference

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is MIT – no restrictions

Best for

  • Chatbots with limited GPU memory
  • Rapid prototyping of instruction‑tuned LLMs
  • Educational demos

Who it’s for. Developers and researchers who need a small, instruction‑tuned Phi model that can run on modest hardware. The model is suitable for local deployment and experimentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.8 GB 4.6 GB
Fits Get file →
IQ1_M0.9 GB 4.6 GB
Fits Get file →
IQ2_XXS1.0 GB 4.8 GB
Fits Get file →
IQ2_XS1.2 GB 4.9 GB
Fits Get file →
IQ2_S1.2 GB 4.9 GB
Fits Get file →
IQ2_M1.3 GB 5.0 GB
Fits Get file →
Q2_K1.4 GB 5.1 GB
Fits Get file →
IQ3_XXS1.5 GB 5.2 GB
Fits Get file →
IQ3_XS1.6 GB 5.3 GB
Fits Get file →
IQ3_S1.7 GB 5.4 GB
Fits Get file →
Q3_K_S1.7 GB 5.4 GB
Fits Get file →
IQ3_M1.9 GB 5.6 GB
Fits Get file →
Q3_K_M2.0 GB 5.7 GB
Fits Get file →
IQ4_XS2.1 GB 5.8 GB
Fits Get file →
Q3_K_L2.1 GB 5.8 GB
Fits Get file →
IQ4_NL2.2 GB 5.9 GB
Fits Get file →
Q4_02.2 GB 5.9 GB
Fits Get file →
Q4_K_S2.2 GB 5.9 GB
Fits Get file →
Q4_K_M2.4 GB 6.1 GB
Fits Get file →
Q5_02.6 GB 6.4 GB
Fits Get file →
Q5_K_S2.6 GB 6.4 GB
Fits Get file →
Q5_K_M2.8 GB 6.5 GB
Fits Get file →
Q6_K3.1 GB 6.9 GB
Fits Get file →
Q8_04.1 GB 7.8 GB
Tight Get file →

For 8 GB VRAM, use IQ1_S (0.84 GB file, 4.6 GB memory) or IQ1_M (0.92 GB file, 4.6 GB memory). If 12 GB VRAM is available, IQ2_S (1.22 GB file, 4.9 GB memory) or Q3_K_S (1.68 GB file, 5.4 GB memory) provide better precision. Larger quants such as Q5_K_M (2.82 GB file, 6.5 GB memory) require 16 GB or more.

What GPU do you need for Phi 3 mini 128k 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: the best quant that fits is Q4_K_S (2.2 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 7.8 GB in use).

Which Phi 3 mini 128k instruct quant should you choose?

Q4_K_M is the usual starting point for Phi 3 mini 128k instruct: it balances file size and quality well. Here it is a 2.4 GB file.

The Q8_0 file is 4.1 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 IQ1_S at 0.8 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
Parameters3.82B
Layers32
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bymmnga
FamilyPhi
Licensemit
Downloads (HF)2,480
Last updated2024-04-24

Frequently asked questions about Phi 3 mini 128k instruct

How much VRAM does Phi 3 mini 128k instruct need?

About 6.1 GB at Q4_K_M with an 8K context window. That is the 2.4 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 mini 128k instruct on an 8 GB GPU?

Yes, with Q8_0: the 4.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Phi 3 mini 128k instruct GGUF?

It depends on the quant: IQ1_S is 0.8 GB, IQ1_M is 0.9 GB, IQ2_XXS is 1.0 GB, IQ2_XS is 1.2 GB, IQ2_S is 1.2 GB, IQ2_M is 1.3 GB and 18 more.

What context length does Phi 3 mini 128k instruct support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download Phi 3 mini 128k instruct GGUF?

The files are on Hugging Face in the mmnga/Phi-3-mini-128k-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 mini 128k 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 mini 128k instruct on 8 GB VRAM?

Yes, the IQ1_S or IQ1_M quant uses about 4.6 GB of VRAM at 8k context, which fits within 8 GB. For larger context, VRAM usage will increase.

Does this model support image input?

No, the model does not have vision capabilities and only processes text.

What license applies to this model?

The model is released under the MIT license, allowing free use and modification.

Similar models

Browse all →

More from mmnga

All by mmnga →

More Phi models

All Phi →

Other small models

All small models →