PH

calme 2.2 phi3 4b

PhiGGUF by MaziyarPanahiUpdated 2024-07-20
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturephi3
Smallest quant1.4 GB
Quick answer

calme 2.2 phi3 4b needs about 6.1 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 11 quants, from 1.4 GB (Q2_K) to 7.6 GB.

Fine‑tuned Phi‑3‑mini 4B for instruction following

calme 2.2 phi3 4b is a DPO fine‑tune of microsoft/Phi-3-mini-4k-instruct. It runs with a 4096 token context and is available in multiple GGUF quantisations. The model is 3.82 billion parameters and supports the ChatML prompt template.

Good at

  • Instruction following
  • Short‑form dialogue
  • Lightweight inference

Limits

  • No vision support
  • License not specified
  • Requires 8 k context for memory estimates

Best for

  • Local chatbot demos
  • Rapid prototyping
  • Low‑cost inference

Who it’s for. Developers and hobbyists who need a small, instruction‑tuned Phi‑3 model for local deployment. The model is ideal for those using llama.cpp or llama‑cpp‑python for GPU‑accelerated inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.4 GB 3.5 GB
Fits Get file →
Q3_K_S1.7 GB 3.8 GB
Fits Get file →
Q3_K_M2.0 GB 4.1 GB
Fits Get file →
Q3_K_L2.1 GB 4.2 GB
Fits Get file →
Q4_K_S2.2 GB 4.3 GB
Fits Get file →
Q4_K_M2.4 GB 4.5 GB
Fits Get file →
Q5_K_S2.6 GB 4.8 GB
Fits Get file →
Q5_K_M2.8 GB 4.9 GB
Fits Get file →
Q6_K3.1 GB 5.2 GB
Fits Get file →
Q8_04.1 GB 6.2 GB
Fits Get file →
—7.6 GB 9.8 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (2.39 GB file, ~6.1 GB RAM). With 12 GB VRAM Q5_K_M (2.82 GB file, ~6.5 GB RAM) gives higher quality. If memory is very tight, Q2_K (1.42 GB file, ~5.1 GB RAM) is the lightest option.

What GPU do you need for calme 2.2 phi3 4b?

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 the main file (7.6 GB file, about 11.4 GB in use).

Which calme 2.2 phi3 4b quant should you choose?

Q4_K_M is the usual starting point for calme 2.2 phi3 4b: it balances file size and quality well. Here it is a 2.4 GB file.

The Q8_0 file is 4.1 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 1.4 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

Architecturephi3
Parameters3.82B
Layers32
Trained context4,096 tokens
KV cache (fp16)384 KB per token

Source

Quantized byMaziyarPanahi
FamilyPhi
Downloads (HF)2,581
Last updated2024-07-20

Frequently asked questions about calme 2.2 phi3 4b

How much VRAM does calme 2.2 phi3 4b need?

About 6.1 GB at Q4_K_M with an 8K context window. That is the 2.4 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 calme 2.2 phi3 4b 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 calme 2.2 phi3 4b GGUF?

It depends on the quant: Q2_K is 1.4 GB, Q3_K_S is 1.7 GB, Q3_K_M is 2.0 GB, Q3_K_L is 2.1 GB, Q4_K_S is 2.2 GB, Q4_K_M is 2.4 GB and 5 more.

What context length does calme 2.2 phi3 4b 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 calme 2.2 phi3 4b GGUF?

The files are on Hugging Face in the MaziyarPanahi/calme-2.2-phi3-4b-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 this model on 8 GB VRAM?

Yes, the Q4_K_M quantisation requires about 6.1 GB of VRAM at 8 k context, which fits in 8 GB.

Does this model support image input?

No, the model has no vision capabilities.

What prompt format does it use?

It uses the ChatML prompt template.

Other GGUFs of calme-2.2-phi3-4b

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Phi models

All Phi →

Other small models

All small models →