PH

Phi 3.5 Mini instruct_Uncensored

PhiGGUF by bartowskiUpdated 2024-08-22
Download on Hugging Face
Parameters3.82B
Context128K
Layers32
Architecturephi3
Smallest quant1.3 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 20 quants, from 1.3 GB (IQ2_M) to 7.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Phi 3.5 Mini instruct_Uncensored – a 3.9B parameter LLM in the Phi family

Phi 3.5 Mini instruct_Uncensored is a 3.9 billion‑parameter model based on the phi3 architecture. It was trained on 131 072 context tokens and released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations ranging from IQ2_M to F16.

Good at

  • Instruction following
  • Low‑latency inference on modest GPUs
  • Compact model size

Limits

  • No vision support
  • Requires 8 k context for memory estimates
  • Uncensored content may produce sensitive outputs

Best for

  • Chatbot prototypes
  • Rapid prototyping of instruction‑based tasks
  • Embedded inference on edge devices

Who it’s for. Developers and researchers who need a small, instruction‑oriented Phi model for local deployment. The model is suitable for applications that require quick responses and can tolerate uncensored content.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M1.3 GB 5.0 GB
Fits Get file →
Q2_K1.4 GB 5.1 GB
Fits Get file →
Q2_K_L1.5 GB 5.2 GB
Fits Get file →
IQ3_XS1.6 GB 5.3 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 →
Q3_K_XL2.2 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 →
Q4_K_L2.5 GB 6.2 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 →
Q5_K_L2.9 GB 6.6 GB
Fits Get file →
Q6_K3.1 GB 6.9 GB
Fits Get file →
Q6_K_L3.2 GB 6.9 GB
Fits Get file →
Q8_04.1 GB 7.8 GB
Tight Get file →
F167.6 GB 11.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (2.39 GB) or Q4_K_L (2.47 GB). If you have 12 GB VRAM, Q5_K_M (2.82 GB) or Q5_K_L (2.88 GB) provide higher quality. For 16 GB VRAM, Q6_K (3.14 GB) or Q6_K_L (3.18 GB) are recommended. Memory estimates are approximate.

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 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 F16 (7.6 GB file, about 11.4 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 IQ2_M at 1.3 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
Licenseapache-2.0
Downloads (HF)6,996
Last updated2024-08-22

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: IQ2_M is 1.3 GB, Q2_K is 1.4 GB, Q2_K_L is 1.5 GB, IQ3_XS is 1.6 GB, Q3_K_S is 1.7 GB, IQ3_M is 1.9 GB and 14 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 bartowski/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 Phi 3.5 Mini instruct_Uncensored on 8 GB VRAM?

Yes, use a quant such as Q4_K_M or Q4_K_L, which fit within 8 GB VRAM and provide a good balance of size and performance.

What is the maximum context length supported by this model?

The model was trained with 131 072 context tokens, so that is the maximum context length it can handle.

Is this model suitable for vision tasks?

No, Phi 3.5 Mini instruct_Uncensored does not support vision inputs.

Other GGUFs of Phi-3.5-mini-instruct_Uncensored

Similar models

Browse all →

More from bartowski

All by bartowski →

More Phi models

All Phi →

Other small models

All small models →