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

Melvin56/GLM-Z1-9B-0414-abliterated-GGUF

Melvin56 Glm 9B GGUF 33K 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/Melvin56%2FGLM-Z1-9B-0414-abliterated-GGUF"
Response includes
  • classification m8
  • files 14
  • hub_downloads_all_time 2,996
  • author_summary 28 models
  • readme_text full
Try next
GET/models?author=Melvin56
All 28 models by Melvin56
 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)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
Why this label 3 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.
  • 'abliterated' in name/tags
  • is_gguf=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
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
458 last 30d - stable
Likes
1
Model age
17mo ago
created 2025-04-22
Downloads over time
Now3.1K→from17↑18,006%
01.1K2.3K3.4K17 on Apr 16, 20253.1K on Oct 113.1K on Oct 9Apr '25Jul '25Oct '25JanAprJulOct
Apr 16, 2025 → Oct 11 · 117 snapshots · spans 543 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

THUDM/GLM-Z1-9B-0414 this lineage
Melvin56/GLM-Z1-9B-0414-abliterated-GGUF↓ 458

Metadata

License
mit
Languages
zh en
Quantizations
BF16 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf abliterated uncensored text-generation zh en base_model:zai-org/GLM-Z1-9B-0414 base_model:quantized:zai-org/GLM-Z1-9B-0414 license:mit endpoints_compatible region:us

Related

Other by Melvin56
DeepSeek-R1-Distill-Qwen-7B-abliterated-v2-GGUF 4K Phi-4-mini-instruct-abliterated-GGUF 1K GLM-4-9B-0414-abliterated-GGUF 988 Qwen2.5-Coder-7B-Instruct-abliterated-Q4_K_M-GGUF 487 Qwen3-8B-abliterated-GGUF 451
Total size
75.9 GB
Files
14
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2025-04-26 07:36
Source huggingface.co/Melvin56/GLM-Z1-9B-0414-abliterated-GGUF ↗ Base model THUDM/GLM-Z1-9B-0414 ↗

Files by quantization

BF16 1 file 17.5 GB
glm-z1-9b-0414-abliterated-BF16.gguf 17.5 GB 4cef9917 download
Q8_0 1 file 9.31 GB
glm-z1-9b-0414-abliterated-Q8_0.gguf 9.31 GB e18d33f9 download
Q6_K 1 file 7.70 GB
glm-z1-9b-0414-abliterated-Q6_K.gguf 7.70 GB b399b0b0 download
Q5_K 2 files 12.8 GB
glm-z1-9b-0414-abliterated-Q5_K_M.gguf 6.57 GB 567b8c6f download
glm-z1-9b-0414-abliterated-Q5_K_S.gguf 6.24 GB e86f6c82 download
Q4_K 2 files 11.1 GB
glm-z1-9b-0414-abliterated-Q4_K_M.gguf 5.74 GB 0b490943 download
glm-z1-9b-0414-abliterated-Q4_K_S.gguf 5.36 GB 7cdb9d82 download
Q3_K 3 files 13.7 GB
glm-z1-9b-0414-abliterated-Q3_K_L.gguf 4.84 GB 8f8aa7b2 download
glm-z1-9b-0414-abliterated-Q3_K_M.gguf 4.63 GB a77d5cc8 download
glm-z1-9b-0414-abliterated-Q3_K_S.gguf 4.28 GB 78212945 download
Q2_K 1 file 3.73 GB
glm-z1-9b-0414-abliterated-Q2_K.gguf 3.73 GB 82efccbf download
Auxiliary files 3 files 5.23 MB
imatrix.dat 5.22 MB b0d9a028 download
.gitattributes 2.33 KB bd469233 download
README.md 1.38 KB 82972459 download

README current version from Hugging Face

license: mit
language:

  • zh
  • en
    pipeline_tag: text-generation
    base_model:
  • THUDM/GLM-Z1-9B-0414
    library_name: transformers
    tags:
  • abliterated
  • uncensored

Melvin56/GLM-Z1-9B-0414-abliterated-GGUF

Original Model : huihui-ai/GLM-Z1-9B-0414-abliterated

Llama.cpp build: 558a7647 (5190)

I used imatrix to create all these quants using this Dataset.

Update-01
  * [Fixed Quant] Re-quantized all quants with build: 558a7647 (5190)
CPU (AVX2) CPU (ARM NEON) Metal cuBLAS rocBLAS SYCL CLBlast Vulkan Kompute
K-quants ✅ ✅ ✅ ✅ ✅ ✅ ✅ 🐢5 ✅ 🐢5 ❌
I-quants ✅ 🐢4 ✅ 🐢4 ✅ 🐢4 ✅ ✅ Partial¹ ❌ ❌ ❌ 
✅: feature works
🚫: feature does not work
❓: unknown, please contribute if you can test it youself
🐢: feature is slow
¹: IQ3_S and IQ1_S, see #5886
²: Only with -ngl 0
³: Inference is 50% slower
⁴: Slower than K-quants of comparable size
⁵: Slower than cuBLAS/rocBLAS on similar cards
⁶: Only q8_0 and iq4_nl

README history 3 versions

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

  1. 2025-04-26Update README.mdc00d7071.4 KB
    Loading...
  2. 2025-04-22Update README.mda47c1b01.6 KB
    Loading...
  3. 2025-04-22Upload folder using huggingface_hub81820554.9 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