dolphin-2.9.2-Phi-3-Medium needs about 8.5 GB of memory at IQ3_M (a 6.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 3.1 GB (IQ1_S) to 27.9 GB.
14B Phi‑3 Medium model fine‑tuned as Dolphin 2.9.2 for instruction and coding
Dolphin‑2.9.2‑Phi‑3‑Medium is a 14 billion‑parameter Llama‑style model fine‑tuned on Phi‑3‑Medium‑Instruct‑4k. It supports instruction following, coding, and function calling. The model is released under the MIT license and uses the ChatML prompt template.
Good at
- Instruction following
- Coding tasks
- Function calling
Limits
- 4 k context length
- No vision support
- Requires alignment layer for safe deployment
Best for
- Chatbot prototypes
- Code generation utilities
- API function‑calling workflows
Who it’s for. Developers and researchers who need a medium‑size Phi‑3 variant with coding and instruction capabilities. The model is suitable for local deployment via llama.cpp and requires a user‑implemented alignment layer for safe use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.1 GB | 4.4 GB | Fits | Get file → | |
| IQ1_M | 3.3 GB | 4.7 GB | Fits | Get file → | |
| IQ2_XXS | 3.8 GB | 5.1 GB | Fits | Get file → | |
| IQ2_XS | 4.2 GB | 5.5 GB | Fits | Get file → | |
| IQ2_S | 4.4 GB | 5.7 GB | Fits | Get file → | |
| IQ2_M | 4.8 GB | 6.1 GB | Fits | Get file → | |
| Q2_K_S | 4.8 GB | 6.2 GB | Fits | Get file → | |
| Q2_K | 5.2 GB | 6.5 GB | Fits | Get file → | |
| IQ3_XXS | 5.4 GB | 6.8 GB | Fits | Get file → | |
| IQ3_XS | 5.8 GB | 7.1 GB | Fits | Get file → | |
| Q3_K_S | 6.1 GB | 7.4 GB | Tight | Get file → | |
| IQ3_S | 6.1 GB | 7.4 GB | Tight | Get file → | |
| IQ3_M | 6.3 GB | 7.6 GB | Tight | Get file → | |
| Q3_K | 6.8 GB | 8.1 GB | Too big | Get file → | |
| Q3_K_L | 7.3 GB | 8.7 GB | Too big | Get file → | |
| IQ4_XS | 7.5 GB | 8.8 GB | Too big | Get file → | |
| IQ4_NL | 7.9 GB | 9.3 GB | Too big | Get file → | |
| Q4_K_S | 8.0 GB | 9.3 GB | Too big | Get file → | |
| Q4_K | 8.4 GB | 9.7 GB | Too big | Get file → | |
| Q5_K_S | 9.6 GB | 11.0 GB | Too big | Get file → | |
| Q5_K | 9.9 GB | 11.2 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 8 GB VRAM, use IQ1_S (3.05 GB) or IQ1_M (3.33 GB). For 12 GB VRAM, IQ2_M (4.78 GB) or Q2_K (5.20 GB) are suitable. For 16 GB VRAM, Q3_K (6.75 GB) or Q4_K (8.40 GB) provide higher quality. Memory estimates are approximate.
What GPU do you need for dolphin-2.9.2-Phi-3-Medium?
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 (3.8 GB file, about 6.0 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 dolphin-2.9.2-Phi-3-Medium quant should you choose?
IQ3_M (6.3 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 3.1 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 dolphin-2.9.2-Phi-3-Medium
How much VRAM does dolphin-2.9.2-Phi-3-Medium need?
About 8.5 GB at IQ3_M with an 8K context window. That is the 6.3 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 dolphin-2.9.2-Phi-3-Medium 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 dolphin-2.9.2-Phi-3-Medium GGUF?
It depends on the quant: IQ1_S is 3.1 GB, IQ1_M is 3.3 GB, IQ2_XXS is 3.8 GB, IQ2_XS is 4.2 GB, IQ2_S is 4.4 GB, IQ2_M is 4.8 GB and 19 more.
What context length does dolphin-2.9.2-Phi-3-Medium 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 dolphin-2.9.2-Phi-3-Medium GGUF?
The files are on Hugging Face in the legraphista/dolphin-2.9.2-Phi-3-Medium-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 dolphin-2.9.2-Phi-3-Medium 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 Dolphin‑2.9.2 on 8 GB VRAM?
Yes, with IQ1_S or IQ1_M quantizations the model file is under 4 GB and requires about 5–5.5 GB VRAM at 8 k context.
Does the model support vision?
No, the model has no vision capabilities and is text‑only.
What license applies to this model?
The model is released under the MIT license, allowing free use and modification.