Llama Phi 3 DoRA needs about 6.0 GB of memory at Q4_K_M (a 2.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 1.4 GB (Q2_K) to 7.6 GB (F16).
Llama Phi 3 DoRA – 3.82B parameter Llama model in GGUF format
Llama Phi 3 DoRA is a 3.82B parameter Llama model quantized for efficient inference. It supports a 4096 token context window and is released under the MIT license. The model is available in multiple quantizations for different memory budgets.
Good at
- Fast inference on modest GPUs
- Low memory footprint with Q4_K and IQ3 variants
- Consistent performance across quant levels
Limits
- No vision capabilities
- Context limited to 4096 tokens
- Requires llama.cpp for local use
Best for
- Chat assistants on laptops
- Rapid prototyping of LLM applications
- Testing new quantization schemes
Who it’s for. Developers and researchers who need a lightweight Llama model for local deployment. The model is suitable for those who prefer open-source licensing and want to experiment with different quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.4 GB | 3.6 GB | Fits | Get file → | |
| IQ3_XS | 1.6 GB | 3.7 GB | Fits | Get file → | |
| IQ3_S | 1.7 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_S | 1.7 GB | 3.8 GB | Fits | Get file → | |
| IQ3_M | 1.8 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_M | 1.9 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_L | 2.0 GB | 4.2 GB | Fits | Get file → | |
| IQ4_XS | 2.1 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_S | 2.2 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_M | 2.3 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_S | 2.6 GB | 4.8 GB | Fits | Get file → | |
| Q5_K_M | 2.7 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 3.1 GB | 5.2 GB | Fits | Get file → | |
| Q8_0 | 4.1 GB | 6.2 GB | Fits | Get file → | |
| F16 | 7.6 GB | 9.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K (file size 2.19 GB, estimated memory 5.9 GB) or IQ3_S (1.68 GB, 5.4 GB). If 12 GB VRAM is available, Q5_K_M (2.72 GB, 6.4 GB) offers higher precision. Larger GPUs can run Q8_0 (4.06 GB, 7.8 GB) for full‑precision performance.
What GPU do you need for Llama Phi 3 DoRA?
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_M (2.3 GB file, about 6.0 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 F16 (7.6 GB file, about 11.4 GB in use).
Which Llama Phi 3 DoRA quant should you choose?
Q4_K_M is the usual starting point for Llama Phi 3 DoRA: it balances file size and quality well. Here it is a 2.3 GB file.
The Q8_0 file is 4.1 GB, about 1.8 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 1.4 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 Llama Phi 3 DoRA
How much VRAM does Llama Phi 3 DoRA need?
About 6.0 GB at Q4_K_M with an 8K context window. That is the 2.3 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 Llama Phi 3 DoRA 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 Llama Phi 3 DoRA GGUF?
It depends on the quant: Q2_K is 1.4 GB, IQ3_XS is 1.6 GB, IQ3_S is 1.7 GB, Q3_K_S is 1.7 GB, IQ3_M is 1.8 GB, Q3_K_M is 1.9 GB and 9 more.
What context length does Llama Phi 3 DoRA 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 Llama Phi 3 DoRA GGUF?
The files are on Hugging Face in the mradermacher/Llama-Phi-3_DoRA-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 Llama Phi 3 DoRA 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 Llama Phi 3 DoRA on 8 GB VRAM?
Yes, the Q4_K quant requires about 5.9 GB of VRAM at 8k context, which fits within an 8 GB GPU.
Does this model support vision tasks?
No, Llama Phi 3 DoRA is a text-only model with no vision capabilities.
What license does the model use?
The model is released under the MIT license, allowing free use and modification.