PH

Phi 3.5 Mini instruct_Uncensored

PhiGGUF by RichardErkhovUpdated 2024-08-24
Download on Hugging Face
Parameters3.82B
Context128K
Layers32
Architecturephi3
Smallest quant1.4 GB
Quick answer

Phi 3.5 Mini instruct_Uncensored 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 22 quants, from 1.4 GB (Q2_K) to 4.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Phi 3.5 Mini instruct_Uncensored – 3.82B parameter LLM

Phi 3.5 Mini instruct_Uncensored is a 3.82B parameter language model based on the phi3 architecture. It supports a 131072 token context window and is released under the apache-2.0 license. The model is uncensored with a censorship level of low‑medium.

Good at

  • Short‑form instruction following
  • High‑token‑count context handling
  • Uncensored content generation

Limits

  • No vision support
  • Large VRAM requirement for higher quants
  • No additional training data beyond uncensoring

Best for

  • Chatbot development
  • Long‑form content drafting
  • Research prototyping

Who it’s for. Developers and researchers needing a lightweight, instruction‑oriented model with a large context window. The model is suitable for local deployment on systems with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.4 GB 5.1 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_K2.0 GB 5.7 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 →
Q4_02.2 GB 5.9 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_K2.4 GB 6.1 GB
Fits Get file →
Q4_K_M2.4 GB 6.1 GB
Fits Get file →
Q4_12.4 GB 6.1 GB
Fits Get file →
Q5_02.6 GB 6.4 GB
Fits Get file →
Q5_K_S2.6 GB 6.4 GB
Fits Get file →
Q5_K2.8 GB 6.5 GB
Fits Get file →
Q5_K_M2.8 GB 6.5 GB
Fits Get file →
Q5_12.9 GB 6.6 GB
Fits Get file →
Q6_K3.1 GB 6.9 GB
Fits Get file →
Q8_04.1 GB 7.8 GB
Tight Get file →

For 8 GB VRAM, use Q4_K or Q4_K_M (file size 2.39 GB, memory 6.1 GB). With 12 GB VRAM, Q5_K or Q5_K_M (file size 2.82 GB, memory 6.5 GB) is recommended. For 16 GB VRAM, Q6_K (file size 3.14 GB, memory 6.9 GB) provides higher quality.

What GPU do you need for Phi 3.5 Mini instruct_Uncensored?

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 IQ4_NL (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).

Which Phi 3.5 Mini instruct_Uncensored quant should you choose?

Q4_K_M is the usual starting point for Phi 3.5 Mini instruct_Uncensored: 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 context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized byRichardErkhov
FamilyPhi
Licenseapache-2.0
Downloads (HF)742
Last updated2024-08-24

Frequently asked questions about Phi 3.5 Mini instruct_Uncensored

How much VRAM does Phi 3.5 Mini instruct_Uncensored 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 3.5 Mini instruct_Uncensored 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 3.5 Mini instruct_Uncensored GGUF?

It depends on the quant: Q2_K is 1.4 GB, IQ3_XS is 1.6 GB, IQ3_S is 1.7 GB, Q3_K_S is 1.7 GB, IQ3_M is 1.9 GB, Q3_K is 2.0 GB and 16 more.

What context length does Phi 3.5 Mini instruct_Uncensored 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 3.5 Mini instruct_Uncensored GGUF?

The files are on Hugging Face in the RichardErkhov/SicariusSicariiStuff_-_Phi-3.5-mini-instruct_Uncensored-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 3.5 Mini instruct_Uncensored use?

Hugging Face lists the license as apache-2.0. 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 this model on 8 GB VRAM?

Yes, using Q4_K or Q4_K_M quantizations which require approximately 6.1 GB of VRAM at 8 k context.

What license does the model use?

The model is released under the apache-2.0 license.

Does the model support vision tasks?

No, the model does not support vision inputs.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Phi models

All Phi →

Other small models

All small models →