Phi 3 mini 128k 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. Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
Phi 3 mini 128k instruct IMat – 3.8B parameter instruction model
Phi 3 mini 128k instruct IMat is a 3.82 billion‑parameter model from the Phi family. It supports a 131072‑token context length and is optimized for instruction following. The model is released under the MIT license and is available in multiple GGUF quantizations.
Good at
- Instruction following
- Reasoning and logic
- Long‑context handling
Limits
- No vision support
- Requires 8k context for memory estimates
- MIT license only for non‑commercial use
Best for
- Chatbots with long context
- Research on instruction tuning
- Low‑latency inference on GPUs
Who it’s for. Developers and researchers needing a lightweight Phi model for English instruction tasks. The model is suitable for environments with limited VRAM and for applications that require strong reasoning capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.8 GB | 4.6 GB | Fits | Get file → | |
| IQ1_M | 0.9 GB | 4.6 GB | Fits | Get file → | |
| IQ2_XXS | 1.0 GB | 4.8 GB | Fits | Get file → | |
| IQ2_XS | 1.2 GB | 4.9 GB | Fits | Get file → | |
| IQ2_S | 1.2 GB | 4.9 GB | Fits | Get file → | |
| IQ2_M | 1.3 GB | 5.0 GB | Fits | Get file → | |
| Q2_K_S | 1.3 GB | 5.0 GB | Fits | Get file → | |
| Q2_K | 1.4 GB | 5.1 GB | Fits | Get file → | |
| IQ3_XXS | 1.5 GB | 5.2 GB | Fits | Get file → | |
| IQ3_XS | 1.6 GB | 5.3 GB | Fits | Get file → | |
| IQ3_S | 1.7 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_S | 1.7 GB | 5.4 GB | Fits | Get file → | |
| IQ3_M | 1.9 GB | 5.6 GB | Fits | Get file → | |
| Q3_K | 2.0 GB | 5.7 GB | Fits | Get file → | |
| IQ4_XS | 2.1 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_L | 2.1 GB | 5.8 GB | Fits | Get file → | |
| IQ4_NL | 2.2 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_S | 2.2 GB | 5.9 GB | Fits | Get file → | |
| Q4_K | 2.4 GB | 6.1 GB | Fits | Get file → | |
| Q5_K_S | 2.6 GB | 6.4 GB | Fits | Get file → | |
| Q5_K | 2.8 GB | 6.5 GB | Fits | Get file → | |
| Q6_K | 3.1 GB | 6.9 GB | Fits | Get file → | |
| Q8_0 | 4.1 GB | 7.8 GB | Tight | Get file → | |
| BF16 | 7.6 GB | 11.4 GB | Too big | Get file → | |
| — | 7.6 GB | 11.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K or Q5_K_S (file sizes 2.39 GB and 2.64 GB, memory ~6.1 GB and 6.4 GB). For 4 GB VRAM, use IQ1_S or IQ1_M (file sizes 0.84 GB and 0.92 GB, memory ~4.6 GB). Larger models like Q8_0 or BF16 require >7 GB VRAM.
What GPU do you need for Phi 3 mini 128k 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 128k 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
Source
Frequently asked questions about Phi 3 mini 128k instruct IMat
How much VRAM does Phi 3 mini 128k 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 128k 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 128k 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 128k instruct IMat 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 IMat GGUF?
The files are on Hugging Face in the legraphista/Phi-3-mini-128k-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 128k 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 8 GB VRAM?
Yes, quantizations such as Q4_K or Q5_K_S fit within 8 GB VRAM with estimated memory usage of about 6.1 GB and 6.4 GB respectively.
Does the model support vision tasks?
No, the model does not have vision capabilities.
What license applies to this model?
The model is released under the MIT license.