phi 2 logical sft needs about 4.9 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 1.1 GB (Q2_K) to 3.0 GB (Q8_0).
Phi‑2 logical SFT – 2.78 billion‑parameter transformer for QA, chat, and code
Phi‑2 logical SFT is a 2.78 billion‑parameter transformer fine‑tuned for logical reasoning and coding. It supports 4096‑token context and is released under the MIT license. The model is optimized for local inference with GGUF quantisations.
Good at
- Logical reasoning
- Coding tasks
- QA and chat formats
Limits
- No vision support
- Requires 8 k context for memory estimates
- No RLHF fine‑tuning
Best for
- Short‑form Q&A
- Chatbot prototypes
- Code generation snippets
Who it’s for. Researchers and developers needing a small, open‑source model for safety studies or low‑resource inference. The model is suitable for experimentation rather than production use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.1 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_S | 1.3 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_M | 1.4 GB | 3.3 GB | Fits | Get file → | |
| Q3_K_L | 1.6 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_S | 1.6 GB | 3.5 GB | Fits | Get file → | |
| Q4_K_M | 1.7 GB | 3.6 GB | Fits | Get file → | |
| Q5_K_S | 1.9 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_M | 2.0 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 2.3 GB | 4.1 GB | Fits | Get file → | |
| Q8_0 | 3.0 GB | 4.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_S (1.63 GB, ~4.8 GB memory) or Q5_K_S (1.93 GB, ~5.1 GB). For 16 GB VRAM, Q6_K (2.29 GB, ~5.5 GB) or Q8_0 (2.96 GB, ~6.1 GB) provide higher quality. Memory estimates are approximate.
What GPU do you need for phi 2 logical sft?
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 Q6_K (2.3 GB file, about 5.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 6.1 GB in use).
Which phi 2 logical sft quant should you choose?
Q4_K_M is the usual starting point for phi 2 logical sft: it balances file size and quality well. Here it is a 1.7 GB file.
The Q8_0 file is 3.0 GB, about 1.7 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 1.1 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 phi 2 logical sft
How much VRAM does phi 2 logical sft need?
About 4.9 GB at Q4_K_M with an 8K context window. That is the 1.7 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 2 logical sft on an 8 GB GPU?
Yes, with Q8_0: the 3.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of phi 2 logical sft GGUF?
It depends on the quant: Q2_K is 1.1 GB, Q3_K_S is 1.3 GB, Q3_K_M is 1.4 GB, Q3_K_L is 1.6 GB, Q4_K_S is 1.6 GB, Q4_K_M is 1.7 GB and 4 more.
What context length does phi 2 logical sft support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.
Where can I download phi 2 logical sft GGUF?
The files are on Hugging Face in the MaziyarPanahi/phi-2-logical-sft-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 2 logical sft 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 Phi‑2 logical SFT on 8 GB VRAM?
Yes, using Q4_K_S or Q5_K_S quantisations will fit within 8 GB VRAM with an estimated 4.8–5.1 GB memory usage.
Does the model support image inputs?
No, Phi‑2 logical SFT has no vision capability.
Is the model fine‑tuned with reinforcement learning?
No, the model has not been fine‑tuned with RLHF.