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

RichardErkhov/byroneverson_-_glm-4-9b-chat-abliterated-gguf

RichardErkhov Glm 9B 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%2Fbyroneverson_-_glm-4-9b-chat-abliterated-gguf"
Response includes
  • classification m8
  • files 24
  • hub_downloads_all_time 3,324
  • author_summary 257 models
  • readme_text full
Try next
GET/models?author=RichardErkhov
All 257 models by RichardErkhov
 GET/models?family=glm&method=m8
Sibling glm 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
3K
700 last 30d - stable
Likes
0
Model age
2.1y ago
created 2024-09-11
Downloads over time
Now3.5K→from465↑645%
01.3K2.5K3.8K465 on Sep 11, 20243.5K on Oct 113.5K on Oct 10Sep '24Jan '25May '25Sep '25JanMaySep
Sep 11, 2024 → Oct 11 · 148 snapshots · spans 760 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
122 GB
Files
24
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2024-09-11 17:36
Source huggingface.co/RichardErkhov/byroneverson_-_glm-4-9b-chat-abliterated-gguf ↗

Files by quantization

Q8_0 1 file 9.31 GB
glm-4-9b-chat-abliterated.Q8_0.gguf 9.31 GB 7edcb9b9 download
Q6_K 1 file 7.69 GB
glm-4-9b-chat-abliterated.Q6_K.gguf 7.69 GB cd3d8db0 download
Q5_K 3 files 19.5 GB
glm-4-9b-chat-abliterated.Q5_K.gguf 6.65 GB 78fcfa87 download
glm-4-9b-chat-abliterated.Q5_K_M.gguf 6.65 GB 78fcfa87 download
glm-4-9b-chat-abliterated.Q5_K_S.gguf 6.23 GB 80d3cf77 download
Q5 2 files 12.7 GB
glm-4-9b-chat-abliterated.Q5_1.gguf 6.61 GB af568d41 download
glm-4-9b-chat-abliterated.Q5_0.gguf 6.10 GB f95b7ae6 download
Q4_K 3 files 17.0 GB
glm-4-9b-chat-abliterated.Q4_K.gguf 5.82 GB 0cf67c7e download
glm-4-9b-chat-abliterated.Q4_K_M.gguf 5.82 GB 0cf67c7e download
glm-4-9b-chat-abliterated.Q4_K_S.gguf 5.36 GB f8a0c8d2 download
Q4 2 files 10.7 GB
glm-4-9b-chat-abliterated.Q4_1.gguf 5.59 GB 538fa679 download
glm-4-9b-chat-abliterated.Q4_0.gguf 5.08 GB ff698f2f download
IQ4 2 files 10.1 GB
glm-4-9b-chat-abliterated.IQ4_NL.gguf 5.13 GB 18ab922d download
glm-4-9b-chat-abliterated.IQ4_XS.gguf 4.94 GB 463034b3 download
Q3_K 4 files 18.6 GB
glm-4-9b-chat-abliterated.Q3_K_L.gguf 4.92 GB 549df7b4 download
glm-4-9b-chat-abliterated.Q3_K.gguf 4.72 GB 500cceb3 download
glm-4-9b-chat-abliterated.Q3_K_M.gguf 4.72 GB 500cceb3 download
glm-4-9b-chat-abliterated.Q3_K_S.gguf 4.27 GB 44e32e8d download
IQ3 3 files 12.9 GB
glm-4-9b-chat-abliterated.IQ3_M.gguf 4.48 GB 9313fe50 download
glm-4-9b-chat-abliterated.IQ3_S.gguf 4.27 GB eab14fce download
glm-4-9b-chat-abliterated.IQ3_XS.gguf 4.13 GB 2d17e8f2 download
Q2_K 1 file 3.72 GB
glm-4-9b-chat-abliterated.Q2_K.gguf 3.72 GB f50f6944 download
Auxiliary files 2 files 8.61 KB
README.md 5.56 KB 9c9e48f1 download
.gitattributes 3.05 KB 21917ee1 download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

glm-4-9b-chat-abliterated - GGUF

Name Quant method Size
glm-4-9b-chat-abliterated.Q2_K.gguf Q2_K 3.72GB
glm-4-9b-chat-abliterated.IQ3_XS.gguf IQ3_XS 4.13GB
glm-4-9b-chat-abliterated.IQ3_S.gguf IQ3_S 4.27GB
glm-4-9b-chat-abliterated.Q3_K_S.gguf Q3_K_S 4.27GB
glm-4-9b-chat-abliterated.IQ3_M.gguf IQ3_M 4.48GB
glm-4-9b-chat-abliterated.Q3_K.gguf Q3_K 4.72GB
glm-4-9b-chat-abliterated.Q3_K_M.gguf Q3_K_M 4.72GB
glm-4-9b-chat-abliterated.Q3_K_L.gguf Q3_K_L 4.92GB
glm-4-9b-chat-abliterated.IQ4_XS.gguf IQ4_XS 4.94GB
glm-4-9b-chat-abliterated.Q4_0.gguf Q4_0 5.08GB
glm-4-9b-chat-abliterated.IQ4_NL.gguf IQ4_NL 5.13GB
glm-4-9b-chat-abliterated.Q4_K_S.gguf Q4_K_S 5.36GB
glm-4-9b-chat-abliterated.Q4_K.gguf Q4_K 5.82GB
glm-4-9b-chat-abliterated.Q4_K_M.gguf Q4_K_M 5.82GB
glm-4-9b-chat-abliterated.Q4_1.gguf Q4_1 5.59GB
glm-4-9b-chat-abliterated.Q5_0.gguf Q5_0 6.1GB
glm-4-9b-chat-abliterated.Q5_K_S.gguf Q5_K_S 6.23GB
glm-4-9b-chat-abliterated.Q5_K.gguf Q5_K 6.65GB
glm-4-9b-chat-abliterated.Q5_K_M.gguf Q5_K_M 6.65GB
glm-4-9b-chat-abliterated.Q5_1.gguf Q5_1 6.61GB
glm-4-9b-chat-abliterated.Q6_K.gguf Q6_K 7.69GB
glm-4-9b-chat-abliterated.Q8_0.gguf Q8_0 9.31GB

Original model description:

base_model: THUDM/glm-4-9b-chat
pipeline_tag: text-generation
license: other
license_name: glm-4
license_link: https://huggingface.co/THUDM/glm-4-9b-chat/blob/main/LICENSE
language:

  • zh
  • en
    tags:
  • glm
  • chatglm
  • thudm
  • chat
  • abliterated
    library_name: transformers

glm-4-9b-chat-abliterated

Version 1.1 (Updated 9/1/2024): Layer 16 is used for abliteration instead of 20. Refusal mitigation tends to work better with this layer. PCA and cosine similarity tests seem to agree.

Check out the jupyter notebook for details of how this model was abliterated from glm-4-9b-chat.

The python package "tiktoken" is required to quantize the model into gguf format. So I had to create a fork of GGUF My Repo (+tiktoken).

Logo

README history 1 version

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

  1. 2024-09-11uploaded readmec7419de5.6 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