codephiii 2.7b i1 needs about 5.0 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 0.7 GB (IQ1_S) to 2.3 GB (Q6_K).
codephiii 2.7b i1 – a 2.78B phi2 model in GGUF format
codephiii 2.7b i1 is a 2.78B parameter phi2 architecture model. It is available in multiple quantizations ranging from IQ1_S to Q6_K. The model supports a 2048 token context window and is provided by mradermacher on Hugging Face.
Good at
- Code generation
- Text completion
- Programming assistance
Limits
- No vision support
- License not specified
- Context limited to 2048 tokens
Best for
- Developers needing lightweight code models
- Researchers testing phi2 quantizations
- Embedded systems with limited VRAM
Who it’s for. This model is suitable for developers and researchers who require a small, efficient phi2 model for code-related tasks. It is ideal for environments where VRAM is limited and quick inference is needed.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.7 GB | 1.8 GB | Fits | Get file → | |
| IQ1_M | 0.7 GB | 1.9 GB | Fits | Get file → | |
| IQ2_XXS | 0.8 GB | 2.0 GB | Fits | Get file → | |
| IQ2_XS | 0.9 GB | 2.0 GB | Fits | Get file → | |
| IQ2_S | 0.9 GB | 2.1 GB | Fits | Get file → | |
| IQ2_M | 1.0 GB | 2.2 GB | Fits | Get file → | |
| Q2_K_S | 1.0 GB | 2.2 GB | Fits | Get file → | |
| Q2_K | 1.1 GB | 2.3 GB | Fits | Get file → | |
| IQ3_XXS | 1.1 GB | 2.3 GB | Fits | Get file → | |
| IQ3_XS | 1.2 GB | 2.4 GB | Fits | Get file → | |
| IQ3_S | 1.3 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_S | 1.3 GB | 2.4 GB | Fits | Get file → | |
| IQ3_M | 1.4 GB | 2.5 GB | Fits | Get file → | |
| Q3_K_M | 1.5 GB | 2.7 GB | Fits | Get file → | |
| IQ4_XS | 1.5 GB | 2.7 GB | Fits | Get file → | |
| IQ4_NL | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_L | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q4_0 | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q4_K_S | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q4_1 | 1.8 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_M | 1.8 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_S | 1.9 GB | 3.1 GB | Fits | Get file → | |
| Q5_K_M | 2.1 GB | 3.2 GB | Fits | Get file → | |
| Q6_K | 2.3 GB | 3.5 GB | Fits | Get file → |
For 8 GB VRAM, use IQ1_S (0.66 GB file, 3.8 GB memory) or IQ1_M (0.71 GB file, 3.9 GB memory). If 12 GB VRAM is available, Q4_K_M (1.79 GB file, 5 GB memory) offers a good balance of size and performance. Larger models like Q6_K need more than 16 GB VRAM.
What GPU do you need for codephiii 2.7b i1?
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: the best quant that fits is IQ2_XXS (0.8 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (2.3 GB file, about 5.5 GB in use).
Which codephiii 2.7b i1 quant should you choose?
Q4_K_M is the usual starting point for codephiii 2.7b i1: it balances file size and quality well. Here it is a 1.8 GB file.
If memory is tight, the smallest file is IQ1_S at 0.7 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 codephiii 2.7b i1
How much VRAM does codephiii 2.7b i1 need?
About 5.0 GB at Q4_K_M with an 8K context window. That is the 1.8 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 codephiii 2.7b i1 on an 8 GB GPU?
Yes, with Q6_K: the 2.3 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of codephiii 2.7b i1 GGUF?
It depends on the quant: IQ1_S is 0.7 GB, IQ1_M is 0.7 GB, IQ2_XXS is 0.8 GB, IQ2_XS is 0.9 GB, IQ2_S is 0.9 GB, IQ2_M is 1.0 GB and 18 more.
What context length does codephiii 2.7b i1 support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.
Where can I download codephiii 2.7b i1 GGUF?
The files are on Hugging Face in the mradermacher/codephiii-2.7b-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run codephiii 2.7b i1 on 8 GB VRAM?
Yes, the IQ1_S and IQ1_M quantizations fit within 8 GB VRAM with estimated memory usage of 3.8 GB and 3.9 GB respectively.
Does this model support image inputs?
No, codephiii 2.7b i1 does not support vision or image inputs.
Where can I download the quantized files?
Quantized files are available on Hugging Face under the mradermacher/codephiii-2.7b-i1-GGUF repository.