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

RichardErkhov/NLPark_-_Shi-Cis-Kestrel-uncensored-gguf

RichardErkhov GGUF 66K 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%2FNLPark_-_Shi-Cis-Kestrel-uncensored-gguf"
Response includes
  • classification m8
  • files 2
  • hub_downloads_all_time 2,910
  • author_summary 257 models
  • readme_text full
Try next
GET/models?author=RichardErkhov
All 257 models by RichardErkhov
 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
3K
89 last 30d - cooling
Likes
0
Model age
2.2y ago
created 2024-08-08
Downloads over time
Now2.9K→from428↑585%
01.1K2.1K3.2K428 on Aug 14, 20242.9K on Oct 112.9K on Oct 9Aug '24Dec '24Apr '25Aug '25Dec '25AprAug
Aug 14, 2024 → Oct 11 · 152 snapshots · spans 788 days

Metadata

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
0 B
Files
2
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-08-09 09:04
Source huggingface.co/RichardErkhov/NLPark_-_Shi-Cis-Kestrel-uncensored-gguf ↗

Files by quantization

Auxiliary files 2 files 10.9 KB
.gitattributes 6.77 KB bcae250e download
README.md 4.11 KB 903bd822 download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Shi-Cis-Kestrel-uncensored - GGUF

Name Quant method Size
Shi-Cis-Kestrel-uncensored.Q2_K.gguf Q2_K 48.63GB
Shi-Cis-Kestrel-uncensored.IQ3_XS.gguf IQ3_XS 54.34GB
Shi-Cis-Kestrel-uncensored.IQ3_S.gguf IQ3_S 57.39GB
Shi-Cis-Kestrel-uncensored.Q3_K_S.gguf Q3_K_S 57.39GB
Shi-Cis-Kestrel-uncensored.IQ3_M.gguf IQ3_M 60.18GB
Shi-Cis-Kestrel-uncensored.Q3_K.gguf Q3_K 63.25GB
Shi-Cis-Kestrel-uncensored.Q3_K_M.gguf Q3_K_M 63.25GB
Shi-Cis-Kestrel-uncensored.Q3_K_L.gguf Q3_K_L 67.71GB
Shi-Cis-Kestrel-uncensored.IQ4_XS.gguf IQ4_XS 71.23GB
Shi-Cis-Kestrel-uncensored.Q4_0.gguf Q4_0 74.17GB
Shi-Cis-Kestrel-uncensored.IQ4_NL.gguf IQ4_NL 75.08GB
Shi-Cis-Kestrel-uncensored.Q4_K_S.gguf Q4_K_S 75.08GB
Shi-Cis-Kestrel-uncensored.Q4_K.gguf Q4_K 79.83GB
Shi-Cis-Kestrel-uncensored.Q4_K_M.gguf Q4_K_M 79.83GB
Shi-Cis-Kestrel-uncensored.Q4_1.gguf Q4_1 82.31GB
Shi-Cis-Kestrel-uncensored.Q5_0.gguf Q5_0 90.45GB
Shi-Cis-Kestrel-uncensored.Q5_K_S.gguf Q5_K_S 90.45GB
Shi-Cis-Kestrel-uncensored.Q5_K.gguf Q5_K 93.24GB
Shi-Cis-Kestrel-uncensored.Q5_K_M.gguf Q5_K_M 93.24GB
Shi-Cis-Kestrel-uncensored.Q5_1.gguf Q5_1 98.59GB
Shi-Cis-Kestrel-uncensored.Q6_K.gguf Q6_K 107.74GB
Shi-Cis-Kestrel-uncensored.Q8_0.gguf Q8_0 139.34GB

Original model description:

license: unknown
language:

  • en
    pipeline_tag: text-generation
    inference: false
    library_name: transformers
    tags:
  • not-for-all-audiences

Shi-Cis

~140B ...

Chinese, English
uncensored version
Released as an early preview of our v3.1 LLMs.
The v3.1 series covers the "Shi-Ci", "AnFeng" and "Cecilia" LLM products.
The sizes are labelled from small to large "Nano" "Leap" "Pattern" "Avocet "Robin" "Kestrel"

README history 1 version

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

  1. 2024-08-09uploaded readme12206244.1 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