PH

phi 4 mini 3.8b instruct

PhiGGUF by lm-kitUpdated 2025-02-28
Download on Hugging Face
Parameters3.84B
Context128K
Layers32
Architecturephi3
Smallest quant1.7 GB
Quick answer

phi 4 mini 3.8b instruct 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 11 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.

Phi 4 mini 3.8b instruct – lightweight instruction‑tuned LLM

Phi 4 mini 3.8b instruct is a 3.84 billion‑parameter model based on the phi3 architecture. It is released under the MIT license and supports up to 131072 context tokens. The model is available in multiple GGUF quantizations.

Good at

  • Instruction following
  • Short‑form dialogue
  • Code generation

Limits

  • No vision support
  • Large context requires high VRAM
  • No mixture of experts

Best for

  • Chatbots on edge devices
  • Rapid prototyping of LLM features
  • Educational demos

Who it’s for. Developers and researchers who need a small, instruction‑tuned model that can run on modest hardware. The MIT license allows free use and modification.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.7 GB 3.3 GB
Fits Get file →
Q3_K_S1.9 GB 3.5 GB
Fits Get file →
Q3_K_M2.1 GB 3.7 GB
Fits Get file →
Q3_K_L2.2 GB 3.8 GB
Fits Get file →
Q4_K_S2.3 GB 3.9 GB
Fits Get file →
Q4_K_M2.5 GB 4.1 GB
Fits Get file →
Q5_K_S2.7 GB 4.3 GB
Fits Get file →
Q5_K_M2.8 GB 4.4 GB
Fits Get file →
Q6_K3.2 GB 4.7 GB
Fits Get file →
Q8_04.1 GB 5.7 GB
Fits Get file →
F167.7 GB 9.3 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (file size 2.49 GB, estimated 4.1 GB memory). For 12 GB VRAM use Q4_K_S (2.34 GB, 3.9 GB memory). If more memory is available, Q5_K_M (2.85 GB, 4.4 GB memory) offers higher precision.

What GPU do you need for phi 4 mini 3.8b 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: 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 phi 4 mini 3.8b instruct quant should you choose?

Q4_K_M is the usual starting point for phi 4 mini 3.8b instruct: 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

Architecturephi3
Parameters3.84B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized bylm-kit
FamilyPhi
Licensemit
Downloads (HF)1,445
Last updated2025-02-28

Frequently asked questions about phi 4 mini 3.8b instruct

How much VRAM does phi 4 mini 3.8b instruct 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 phi 4 mini 3.8b instruct 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 phi 4 mini 3.8b instruct 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, Q3_K_L is 2.2 GB, Q4_K_S is 2.3 GB, Q4_K_M is 2.5 GB and 5 more.

What context length does phi 4 mini 3.8b 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 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download phi 4 mini 3.8b instruct GGUF?

The files are on Hugging Face in the lm-kit/phi-4-mini-3.8b-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 4 mini 3.8b 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 this model on 8 GB VRAM?

Yes, the Q4_K_M quantization requires approximately 4.1 GB VRAM at 8k context, which fits within 8 GB.

What license does this model use?

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

Does this model support vision tasks?

No, the model has no vision capabilities and is text‑only.

Similar models

Browse all →

More from lm-kit

All by lm-kit →

More Phi models

All Phi →

Other small models

All small models →