Get the app
← back to catalog · registered 2026-08-22 13:56

RichardErkhov/SicariusSicariiStuff_-_Phi-3.5-mini-instruct_Uncensored-gguf

RichardErkhov Phi GGUF 131K ctx
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model. 

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/RichardErkhov%2FSicariusSicariiStuff_-_Phi-3.5-mini-instruct_Uncensored-gguf"
Response includes
  • classification m8
  • files 24
  • hub_downloads_all_time 4,691
  • author_summary 257 models
  • readme_text full
Try next
GET/models?author=RichardErkhov
All 257 models by RichardErkhov
 GET/models?family=phi&method=m8
Sibling phi models · same method
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 2 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • author=richarderkhov (M8 quantization producer)
  • is_gguf=1
How we label → About M8 →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
5K
956 last 30d - stable
Likes
1
Model age
2.1y ago
created 2024-08-24
Downloads over time
Now4.9K→from275↑1,687%
01.8K3.6K5.4K275 on Aug 21, 20244.9K on Oct 11Aug '24Dec '24Apr '25Aug '25Dec '25AprAug
Aug 21, 2024 → Oct 11 · 151 snapshots · spans 781 days

Metadata

Quantizations
IQ3 IQ4 Q2_K Q3_K Q4 Q4_K Q5 Q5_K Q6_K Q8_0
Tags
gguf endpoints_compatible region:us conversational

Related

Other by RichardErkhov
byroneverson_-_gemma-2-27b-it-abliterated-gguf 2K huihui-ai_-_Llama-3.2-1B-Instruct-abliterated-gguf 2K failspy_-_Codestral-22B-v0.1-abliterated-v3-gguf 2K Rupesh2_-_Llama-3.1-8B-Uncensored-gguf 2K huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf 2K
Total size
47.6 GB
Files
24
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2024-08-24 22:01
Source huggingface.co/RichardErkhov/SicariusSicariiStuff_-_Phi-3.5-mini-instruct_Uncensored-gguf ↗

Files by quantization

Q8_0 1 file 3.78 GB
Phi-3.5-mini-instruct_Uncensored.Q8_0.gguf 3.78 GB bfc8e17e download
Q6_K 1 file 2.92 GB
Phi-3.5-mini-instruct_Uncensored.Q6_K.gguf 2.92 GB 04e08f02 download
Q5 2 files 5.14 GB
Phi-3.5-mini-instruct_Uncensored.Q5_1.gguf 2.68 GB 172f94f3 download
Phi-3.5-mini-instruct_Uncensored.Q5_0.gguf 2.46 GB 6655b992 download
Q5_K 3 files 7.70 GB
Phi-3.5-mini-instruct_Uncensored.Q5_K.gguf 2.62 GB 18aa7b7e download
Phi-3.5-mini-instruct_Uncensored.Q5_K_M.gguf 2.62 GB 18aa7b7e download
Phi-3.5-mini-instruct_Uncensored.Q5_K_S.gguf 2.46 GB 0548f2d8 download
Q4 2 files 4.27 GB
Phi-3.5-mini-instruct_Uncensored.Q4_1.gguf 2.24 GB 2e2d362f download
Phi-3.5-mini-instruct_Uncensored.Q4_0.gguf 2.03 GB 79097824 download
Q4_K 3 files 6.50 GB
Phi-3.5-mini-instruct_Uncensored.Q4_K.gguf 2.23 GB d62fdc84 download
Phi-3.5-mini-instruct_Uncensored.Q4_K_M.gguf 2.23 GB d62fdc84 download
Phi-3.5-mini-instruct_Uncensored.Q4_K_S.gguf 2.04 GB 2b7af2f1 download
IQ4 2 files 3.97 GB
Phi-3.5-mini-instruct_Uncensored.IQ4_NL.gguf 2.04 GB d870693b download
Phi-3.5-mini-instruct_Uncensored.IQ4_XS.gguf 1.93 GB e839cd98 download
Q3_K 4 files 7.15 GB
Phi-3.5-mini-instruct_Uncensored.Q3_K_L.gguf 1.94 GB 99d41a2f download
Phi-3.5-mini-instruct_Uncensored.Q3_K.gguf 1.82 GB 1608fc52 download
Phi-3.5-mini-instruct_Uncensored.Q3_K_M.gguf 1.82 GB 1608fc52 download
Phi-3.5-mini-instruct_Uncensored.Q3_K_S.gguf 1.57 GB 65a687a9 download
IQ3 3 files 4.81 GB
Phi-3.5-mini-instruct_Uncensored.IQ3_M.gguf 1.73 GB ac0fa594 download
Phi-3.5-mini-instruct_Uncensored.IQ3_S.gguf 1.57 GB 9018ab29 download
Phi-3.5-mini-instruct_Uncensored.IQ3_XS.gguf 1.51 GB 43c8c1e5 download
Q2_K 1 file 1.32 GB
Phi-3.5-mini-instruct_Uncensored.Q2_K.gguf 1.32 GB 557b2e43 download
Auxiliary files 2 files 10.9 KB
README.md 7.65 KB 7c676892 download
.gitattributes 3.20 KB 2ffd6a89 download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Phi-3.5-mini-instruct_Uncensored - GGUF

Name Quant method Size
Phi-3.5-mini-instruct_Uncensored.Q2_K.gguf Q2_K 1.32GB
Phi-3.5-mini-instruct_Uncensored.IQ3_XS.gguf IQ3_XS 1.51GB
Phi-3.5-mini-instruct_Uncensored.IQ3_S.gguf IQ3_S 1.57GB
Phi-3.5-mini-instruct_Uncensored.Q3_K_S.gguf Q3_K_S 1.57GB
Phi-3.5-mini-instruct_Uncensored.IQ3_M.gguf IQ3_M 1.73GB
Phi-3.5-mini-instruct_Uncensored.Q3_K.gguf Q3_K 1.82GB
Phi-3.5-mini-instruct_Uncensored.Q3_K_M.gguf Q3_K_M 1.82GB
Phi-3.5-mini-instruct_Uncensored.Q3_K_L.gguf Q3_K_L 1.94GB
Phi-3.5-mini-instruct_Uncensored.IQ4_XS.gguf IQ4_XS 1.93GB
Phi-3.5-mini-instruct_Uncensored.Q4_0.gguf Q4_0 2.03GB
Phi-3.5-mini-instruct_Uncensored.IQ4_NL.gguf IQ4_NL 2.04GB
Phi-3.5-mini-instruct_Uncensored.Q4_K_S.gguf Q4_K_S 2.04GB
Phi-3.5-mini-instruct_Uncensored.Q4_K.gguf Q4_K 2.23GB
Phi-3.5-mini-instruct_Uncensored.Q4_K_M.gguf Q4_K_M 2.23GB
Phi-3.5-mini-instruct_Uncensored.Q4_1.gguf Q4_1 2.24GB
Phi-3.5-mini-instruct_Uncensored.Q5_0.gguf Q5_0 2.46GB
Phi-3.5-mini-instruct_Uncensored.Q5_K_S.gguf Q5_K_S 2.46GB
Phi-3.5-mini-instruct_Uncensored.Q5_K.gguf Q5_K 2.62GB
Phi-3.5-mini-instruct_Uncensored.Q5_K_M.gguf Q5_K_M 2.62GB
Phi-3.5-mini-instruct_Uncensored.Q5_1.gguf Q5_1 2.68GB
Phi-3.5-mini-instruct_Uncensored.Q6_K.gguf Q6_K 2.92GB
Phi-3.5-mini-instruct_Uncensored.Q8_0.gguf Q8_0 3.78GB

Original model description:

license: apache-2.0
language:

  • en
    pipeline_tag: text-generation
Phi-3.5-mini-instruct (128K) - Uncensored
Dusk Rainbow

This is the basic model, no additional data was used except my uncensoring protocol.

Model Details

  • Censorship level: Low - Medium

  • 6.4 / 10 (10 completely uncensored)

  • UGI score:

    UGI Score

Phi-3.5-mini-instruct_Uncensored is available at the following quantizations:

Support

GPUs too expensive
  • My Ko-fi page ALL donations will go for research resources and compute, every bit is appreciated 🙏🏻

Other stuff

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2024-08-24uploaded readme88a52627.7 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration