PH

Phi 3 mini 4k instruct IMat

PhiGGUF by legraphistaUpdated 2024-05-26
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturephi3
Smallest quant0.8 GB
Quick answer

Phi 3 mini 4k instruct IMat needs about 5.6 GB of memory at IQ3_M (a 1.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.8 GB (IQ1_S) to 7.6 GB.

Phi 3 mini 4k instruct IMat – 3.82B parameter, 4k context, open license

Phi 3 mini 4k instruct IMat is a 3.82B parameter model with a 4096 token context window. It is released under the MIT license and is optimized for instruction following and reasoning tasks. The model is quantized by legraphista and available in multiple GGUF formats.

Good at

  • Instruction following
  • Reasoning and math
  • Low‑latency inference

Limits

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

Best for

  • Chatbots on edge devices
  • Research prototypes
  • Low‑cost inference pipelines

Who it’s for. Developers building lightweight, instruction‑driven AI applications that need strong reasoning capabilities. The model is suitable for commercial and research use in English environments with constrained resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.8 GB 3.0 GB
Fits Get file →
IQ1_M0.9 GB 3.0 GB
Fits Get file →
IQ2_XXS1.0 GB 3.2 GB
Fits Get file →
IQ2_XS1.2 GB 3.3 GB
Fits Get file →
IQ2_S1.2 GB 3.3 GB
Fits Get file →
IQ2_M1.3 GB 3.4 GB
Fits Get file →
Q2_K_S1.3 GB 3.4 GB
Fits Get file →
Q2_K1.4 GB 3.5 GB
Fits Get file →
IQ3_XXS1.5 GB 3.6 GB
Fits Get file →
IQ3_XS1.6 GB 3.7 GB
Fits Get file →
IQ3_S1.7 GB 3.8 GB
Fits Get file →
Q3_K_S1.7 GB 3.8 GB
Fits Get file →
IQ3_M1.9 GB 4.0 GB
Fits Get file →
Q3_K2.0 GB 4.1 GB
Fits Get file →
IQ4_XS2.1 GB 4.2 GB
Fits Get file →
Q3_K_L2.1 GB 4.2 GB
Fits Get file →
IQ4_NL2.2 GB 4.3 GB
Fits Get file →
Q4_K_S2.2 GB 4.3 GB
Fits Get file →
Q4_K2.4 GB 4.5 GB
Fits Get file →
Q5_K_S2.6 GB 4.8 GB
Fits Get file →
Q5_K2.8 GB 4.9 GB
Fits Get file →
Q6_K3.1 GB 5.2 GB
Fits Get file →
Q8_04.1 GB 6.2 GB
Fits Get file →
BF167.6 GB 9.8 GB
Too big Get file →
—7.6 GB 9.8 GB
Too big Get file →

For 8 GB VRAM use IQ1_S or IQ1_M (file size 0.84 GB or 0.92 GB, memory ~4.6 GB). For 12 GB VRAM use Q4_K (file size 2.39 GB, memory ~6.1 GB). For 16 GB VRAM use Q5_K (file size 2.82 GB, memory ~6.5 GB).

What GPU do you need for Phi 3 mini 4k instruct IMat?

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).
  • 12 GB VRAM: the best quant that fits is BF16 (7.6 GB file, about 11.4 GB in use).

Which Phi 3 mini 4k instruct IMat quant should you choose?

IQ3_M (1.9 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 context4,096 tokens
KV cache (fp16)384 KB per token

Source

Quantized bylegraphista
FamilyPhi
Licensemit
Downloads (HF)1,328
Last updated2024-05-26

Frequently asked questions about Phi 3 mini 4k instruct IMat

How much VRAM does Phi 3 mini 4k instruct IMat need?

About 5.6 GB at IQ3_M with an 8K context window. That is the 1.9 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 4k instruct IMat 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 4k instruct IMat 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 19 more.

What context length does Phi 3 mini 4k instruct IMat support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.2 GB at 8K and 1.6 GB at 4K.

Where can I download Phi 3 mini 4k instruct IMat GGUF?

The files are on Hugging Face in the legraphista/Phi-3-mini-4k-instruct-IMat-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 4k instruct IMat 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 4k instruct IMat on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quantizations will fit within 8 GB VRAM with an estimated memory usage of 4.6 GB at 8k context.

Does this model support image inputs?

No, the model 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-mini-4k-instruct

Similar models

Browse all →

More from legraphista

All by legraphista →

More Phi models

All Phi →

Other small models

All small models →