Phi 3 medium 4k instruct IMat needs about 8.7 GB of memory at IQ3_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 3.0 GB (IQ1_S) to 27.9 GB.
Phi 3 medium 4k instruct IMat – 14B parameter, 4K context, MIT licensed
Phi 3 medium 4k instruct IMat is a 14B parameter model with a 4096 token context. It is quantized by llama.cpp using IMatrix. The model is licensed under MIT and supports English instruction following.
Good at
- Reasoning and logic
- Code and math understanding
- Low‑latency inference
Limits
- No vision support
- Requires 8K context for memory estimates
- No explicit language list
Best for
- Chatbots needing quick responses
- Code generation tools
- Research prototypes
Who it’s for. Developers building commercial or research applications that require a lightweight, instruction‑following model. The model is suitable for environments with limited memory and latency constraints.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.0 GB | 4.3 GB | Fits | Get file → | |
| IQ1_M | 3.2 GB | 4.6 GB | Fits | Get file → | |
| IQ2_XXS | 3.7 GB | 5.1 GB | Fits | Get file → | |
| IQ2_XS | 4.1 GB | 5.5 GB | Fits | Get file → | |
| IQ2_S | 4.3 GB | 5.7 GB | Fits | Get file → | |
| IQ2_M | 4.7 GB | 6.1 GB | Fits | Get file → | |
| Q2_K_S | 4.8 GB | 6.1 GB | Fits | Get file → | |
| Q2_K | 5.1 GB | 6.5 GB | Fits | Get file → | |
| IQ3_XXS | 5.5 GB | 6.8 GB | Fits | Get file → | |
| IQ3_XS | 5.8 GB | 7.1 GB | Fits | Get file → | |
| IQ3_S | 6.1 GB | 7.4 GB | Tight | Get file → | |
| Q3_K_S | 6.1 GB | 7.4 GB | Tight | Get file → | |
| IQ3_M | 6.5 GB | 7.8 GB | Tight | Get file → | |
| Q3_K | 6.9 GB | 8.3 GB | Too big | Get file → | |
| IQ4_XS | 7.5 GB | 8.8 GB | Too big | Get file → | |
| Q3_K_L | 7.5 GB | 8.8 GB | Too big | Get file → | |
| IQ4_NL | 7.9 GB | 9.2 GB | Too big | Get file → | |
| Q4_K_S | 8.0 GB | 9.3 GB | Too big | Get file → | |
| Q4_K | 8.6 GB | 9.9 GB | Too big | Get file → | |
| Q5_K_S | 9.6 GB | 11.0 GB | Too big | Get file → | |
| Q5_K | 10.1 GB | 11.4 GB | Too big | Get file → | |
| Q6_K | 11.5 GB | 12.8 GB | Too big | Get file → | |
| Q8_0 | 14.8 GB | 16.2 GB | Too big | Get file → | |
| BF16 | 27.9 GB | 29.3 GB | Too big | Get file → | |
| — | 27.9 GB | 29.3 GB | Too big | Get file → |
For 8GB VRAM, use IQ1_S (2.96 GB) or IQ1_M (3.24 GB). For 16GB VRAM, IQ2_M (4.72 GB) or Q2_K (5.14 GB) are suitable. For 32GB VRAM, Q5_K (10.07 GB) or Q6_K (11.45 GB) provide higher quality.
What GPU do you need for Phi 3 medium 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 IQ2_XXS (3.7 GB file, about 5.9 GB in use).
- 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 (11.5 GB file, about 13.6 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 BF16 (27.9 GB file, about 30.1 GB in use).
Which Phi 3 medium 4k instruct IMat quant should you choose?
IQ3_M (6.5 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 3.0 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
Source
Frequently asked questions about Phi 3 medium 4k instruct IMat
How much VRAM does Phi 3 medium 4k instruct IMat need?
About 8.7 GB at IQ3_M with an 8K context window. That is the 6.5 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 3 medium 4k instruct IMat 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 IMat GGUF?
It depends on the quant: IQ1_S is 3.0 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.7 GB, IQ2_XS is 4.1 GB, IQ2_S is 4.3 GB, IQ2_M is 4.7 GB and 19 more.
What context length does Phi 3 medium 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 1.7 GB at 8K and 0.8 GB at 4K.
Where can I download Phi 3 medium 4k instruct IMat GGUF?
The files are on Hugging Face in the legraphista/Phi-3-medium-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 medium 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 this model on 8GB VRAM?
Yes, using IQ1_S or IQ1_M quantizations which are under 8GB.
Does the model support vision tasks?
No, this model does not include vision capabilities.
What context length does it support?
It supports a 4096 token context length.