PH

Phi 3 Context Obedient RAG

PhiGGUF by bartowskiUpdated 2024-05-11
Download on Hugging Face
Parameters3.82B
Context128K
Layers32
Architecturephi3
Smallest quant0.8 GB
Quick answer

Phi 3 Context Obedient RAG 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 23 quants, from 0.8 GB (IQ1_S) to 15.3 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Phi 3 Context Obedient RAG – 3.82B parameter LLM with 131072 token context

Phi 3 Context Obedient RAG is a 3.82B parameter model from the Phi family. It supports up to 131072 tokens of context and is released under cc‑by‑sa‑4.0. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • RAG‑enabled responses
  • Phi architecture efficiency

Limits

  • No vision support
  • Requires high VRAM for larger quants
  • License requires attribution

Best for

  • Document retrieval tasks
  • Long‑form Q&A
  • Context‑rich chat

Who it’s for. Developers building retrieval‑augmented chatbots or knowledge‑base assistants who need a model that can process very long contexts. The model is suitable for research and production environments that can meet its memory requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.8 GB 4.6 GB
Fits Get file →
IQ1_M0.9 GB 4.6 GB
Fits Get file →
IQ2_XXS1.0 GB 4.8 GB
Fits Get file →
IQ2_XS1.2 GB 4.9 GB
Fits Get file →
IQ2_S1.2 GB 4.9 GB
Fits Get file →
IQ2_M1.3 GB 5.0 GB
Fits Get file →
Q2_K1.4 GB 5.1 GB
Fits Get file →
IQ3_XXS1.5 GB 5.2 GB
Fits Get file →
IQ3_XS1.6 GB 5.3 GB
Fits Get file →
IQ3_S1.7 GB 5.4 GB
Fits Get file →
Q3_K_S1.7 GB 5.4 GB
Fits Get file →
IQ3_M1.9 GB 5.6 GB
Fits Get file →
Q3_K_M2.0 GB 5.7 GB
Fits Get file →
IQ4_XS2.1 GB 5.8 GB
Fits Get file →
Q3_K_L2.1 GB 5.8 GB
Fits Get file →
IQ4_NL2.2 GB 5.9 GB
Fits Get file →
Q4_K_S2.2 GB 5.9 GB
Fits Get file →
Q4_K_M2.4 GB 6.1 GB
Fits Get file →
Q5_K_S2.6 GB 6.4 GB
Fits Get file →
Q5_K_M2.8 GB 6.5 GB
Fits Get file →
Q6_K3.1 GB 6.9 GB
Fits Get file →
Q8_04.1 GB 7.8 GB
Tight Get file →
F3215.3 GB 19.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M (est. 4.6 GB at 8 k context). For 12 GB VRAM, Q4_K_M (est. 6.1 GB) or Q5_K_M (est. 6.5 GB) are suitable. For 16 GB VRAM, Q6_K (est. 6.9 GB) or Q8_0 (est. 7.8 GB) provide higher precision.

What GPU do you need for Phi 3 Context Obedient RAG?

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 Q8_0 (4.1 GB file, about 7.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 7.8 GB in use).
  • 24 GB VRAM: the best quant that fits is F32 (15.3 GB file, about 19.0 GB in use).

Which Phi 3 Context Obedient RAG quant should you choose?

Q4_K_M is the usual starting point for Phi 3 Context Obedient RAG: 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 IQ1_S at 0.8 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 context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bybartowski
FamilyPhi
Downloads (HF)512
Last updated2024-05-11

Frequently asked questions about Phi 3 Context Obedient RAG

How much VRAM does Phi 3 Context Obedient RAG 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 Phi 3 Context Obedient RAG 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 Phi 3 Context Obedient RAG GGUF?

It depends on the quant: IQ1_S is 0.8 GB, IQ1_M is 0.9 GB, IQ2_XXS is 1.0 GB, IQ2_XS is 1.2 GB, IQ2_S is 1.2 GB, IQ2_M is 1.3 GB and 17 more.

What context length does Phi 3 Context Obedient RAG support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download Phi 3 Context Obedient RAG GGUF?

The files are on Hugging Face in the bartowski/Phi-3-Context-Obedient-RAG-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 3 Context Obedient RAG use?

Hugging Face lists the license as cc-by-sa-4.0. 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 3 Context Obedient RAG on 8 GB VRAM?

Yes, the IQ1_S and IQ1_M quantizations use about 4.6 GB at 8 k context, fitting within 8 GB VRAM.

Does the model support vision inputs?

No, the model does not include vision capabilities.

What license does the model use?

The model is released under cc‑by‑sa‑4.0, requiring attribution and share‑alike.

Similar models

Browse all →

More from bartowski

All by bartowski →

More Phi models

All Phi →

Other small models

All small models →