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

RichardErkhov/bunnycore_-_LLama-3.1-8B-HyperNova-abliteration-gguf

RichardErkhov Llama 8B 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%2Fbunnycore_-_LLama-3.1-8B-HyperNova-abliteration-gguf"
Response includes
  • classification m8
  • files 24
  • hub_downloads_all_time 2,521
  • author_summary 257 models
  • readme_text full
Try next
GET/models?author=RichardErkhov
All 257 models by RichardErkhov
 GET/models?family=llama&method=m8
Sibling llama 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
916 last 30d - stable
Likes
0
Model age
2.0y ago
created 2024-09-25
Downloads over time
Now2.7K→from360↑662%
01K2K3K360 on Sep 25, 20242.7K on Oct 11Sep '24Jan '25May '25Sep '25JanMaySep
Sep 25, 2024 → Oct 11 · 146 snapshots · spans 746 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

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
100 GB
Files
24
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2024-09-26 02:53
Source huggingface.co/RichardErkhov/bunnycore_-_LLama-3.1-8B-HyperNova-abliteration-gguf ↗

Files by quantization

Q8_0 1 file 7.95 GB
LLama-3.1-8B-HyperNova-abliteration.Q8_0.gguf 7.95 GB cbf5020d download
Q6_K 1 file 6.14 GB
LLama-3.1-8B-HyperNova-abliteration.Q6_K.gguf 6.14 GB 4a350598 download
Q5 2 files 10.9 GB
LLama-3.1-8B-HyperNova-abliteration.Q5_1.gguf 5.65 GB d3b17209 download
LLama-3.1-8B-HyperNova-abliteration.Q5_0.gguf 5.21 GB dbdc5638 download
Q5_K 3 files 15.9 GB
LLama-3.1-8B-HyperNova-abliteration.Q5_K.gguf 5.34 GB de99a854 download
LLama-3.1-8B-HyperNova-abliteration.Q5_K_M.gguf 5.34 GB de99a854 download
LLama-3.1-8B-HyperNova-abliteration.Q5_K_S.gguf 5.21 GB 98827a43 download
Q4 2 files 9.12 GB
LLama-3.1-8B-HyperNova-abliteration.Q4_1.gguf 4.78 GB 69eb1d18 download
LLama-3.1-8B-HyperNova-abliteration.Q4_0.gguf 4.34 GB dea16541 download
Q4_K 3 files 13.5 GB
LLama-3.1-8B-HyperNova-abliteration.Q4_K.gguf 4.58 GB 2f637ccd download
LLama-3.1-8B-HyperNova-abliteration.Q4_K_M.gguf 4.58 GB 2f637ccd download
LLama-3.1-8B-HyperNova-abliteration.Q4_K_S.gguf 4.37 GB 3f234f74 download
IQ4 2 files 8.56 GB
LLama-3.1-8B-HyperNova-abliteration.IQ4_NL.gguf 4.38 GB 97c2010a download
LLama-3.1-8B-HyperNova-abliteration.IQ4_XS.gguf 4.18 GB 4af53d5d download
Q3_K 4 files 14.9 GB
LLama-3.1-8B-HyperNova-abliteration.Q3_K_L.gguf 4.03 GB 0430201f download
LLama-3.1-8B-HyperNova-abliteration.Q3_K.gguf 3.74 GB ab723f6d download
LLama-3.1-8B-HyperNova-abliteration.Q3_K_M.gguf 3.74 GB ab723f6d download
LLama-3.1-8B-HyperNova-abliteration.Q3_K_S.gguf 3.41 GB dbd1ffef download
IQ3 3 files 10.2 GB
LLama-3.1-8B-HyperNova-abliteration.IQ3_M.gguf 3.52 GB 51d7e975 download
LLama-3.1-8B-HyperNova-abliteration.IQ3_S.gguf 3.43 GB 9cfd7588 download
LLama-3.1-8B-HyperNova-abliteration.IQ3_XS.gguf 3.28 GB bb485efc download
Q2_K 1 file 2.96 GB
LLama-3.1-8B-HyperNova-abliteration.Q2_K.gguf 2.96 GB fe173a22 download
Auxiliary files 2 files 9.38 KB
README.md 6.11 KB a45d83be download
.gitattributes 3.27 KB db8923bb download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

LLama-3.1-8B-HyperNova-abliteration - GGUF

Name Quant method Size
LLama-3.1-8B-HyperNova-abliteration.Q2_K.gguf Q2_K 2.96GB
LLama-3.1-8B-HyperNova-abliteration.IQ3_XS.gguf IQ3_XS 3.28GB
LLama-3.1-8B-HyperNova-abliteration.IQ3_S.gguf IQ3_S 3.43GB
LLama-3.1-8B-HyperNova-abliteration.Q3_K_S.gguf Q3_K_S 3.41GB
LLama-3.1-8B-HyperNova-abliteration.IQ3_M.gguf IQ3_M 3.52GB
LLama-3.1-8B-HyperNova-abliteration.Q3_K.gguf Q3_K 3.74GB
LLama-3.1-8B-HyperNova-abliteration.Q3_K_M.gguf Q3_K_M 3.74GB
LLama-3.1-8B-HyperNova-abliteration.Q3_K_L.gguf Q3_K_L 4.03GB
LLama-3.1-8B-HyperNova-abliteration.IQ4_XS.gguf IQ4_XS 4.18GB
LLama-3.1-8B-HyperNova-abliteration.Q4_0.gguf Q4_0 4.34GB
LLama-3.1-8B-HyperNova-abliteration.IQ4_NL.gguf IQ4_NL 4.38GB
LLama-3.1-8B-HyperNova-abliteration.Q4_K_S.gguf Q4_K_S 4.37GB
LLama-3.1-8B-HyperNova-abliteration.Q4_K.gguf Q4_K 4.58GB
LLama-3.1-8B-HyperNova-abliteration.Q4_K_M.gguf Q4_K_M 4.58GB
LLama-3.1-8B-HyperNova-abliteration.Q4_1.gguf Q4_1 4.78GB
LLama-3.1-8B-HyperNova-abliteration.Q5_0.gguf Q5_0 5.21GB
LLama-3.1-8B-HyperNova-abliteration.Q5_K_S.gguf Q5_K_S 5.21GB
LLama-3.1-8B-HyperNova-abliteration.Q5_K.gguf Q5_K 5.34GB
LLama-3.1-8B-HyperNova-abliteration.Q5_K_M.gguf Q5_K_M 5.34GB
LLama-3.1-8B-HyperNova-abliteration.Q5_1.gguf Q5_1 5.65GB
LLama-3.1-8B-HyperNova-abliteration.Q6_K.gguf Q6_K 6.14GB
LLama-3.1-8B-HyperNova-abliteration.Q8_0.gguf Q8_0 7.95GB

Original model description:

base_model:

  • bunnycore/LLama-3.1-8B-HyperNova
  • grimjim/Llama-3-Instruct-abliteration-LoRA-8B
    library_name: transformers
    tags:
  • mergekit
  • merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the passthrough merge method using bunnycore/LLama-3.1-8B-HyperNova + grimjim/Llama-3-Instruct-abliteration-LoRA-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: bunnycore/LLama-3.1-8B-HyperNova+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
dtype: bfloat16
merge_method: passthrough
models:
  - model: bunnycore/LLama-3.1-8B-HyperNova+grimjim/Llama-3-Instruct-abliteration-LoRA-8B

README history 1 version

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

  1. 2024-09-26uploaded readme3d1419d6.1 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