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

DevQuasar/DavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF

DevQuasar Llama 18.4B GGUF MoE second-order 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/DevQuasar%2FDavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF"
Response includes
  • classification m8
  • files 13
  • hub_downloads_all_time 6,184
  • author_summary 54 models
  • readme_text full
Try next
GET/models?author=DevQuasar
All 54 models by DevQuasar
 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)

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
M1 Direct removal →
Why this label 3 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • author=devquasar (M8 quantization producer)
  • is_gguf=1
  • base_model='DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B' looks abliterated -> assume M1
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
6K
668 last 30d - stable
Likes
1
Model age
16mo ago
created 2025-06-07
Downloads over time
Now6.4K→from1.5K↑329%
1.2K3.1K5K6.9K1.5K on Jul 9, 20256.4K on Oct 13Jul '25Sep '25Nov '25JanMarMayJulSep
Jul 9, 2025 → Oct 13 · 107 snapshots · spans 461 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.

DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B↓ 228 this lineage
DevQuasar/DavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF↓ 668

Metadata

Quantizations
F16 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf text-generation base_model:DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B base_model:quantized:DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B endpoints_compatible region:us conversational

Related

Other by DevQuasar
huihui-ai.Qwen3-8B-abliterated-GGUF 3K huihui-ai.GLM-4-32B-0414-abliterated-GGUF 2K nicoboss.Qwen3-32B-Uncensored-GGUF 1K DavidAU.L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-GGUF 1K huihui-ai.Huihui-Qwen3.5-27B-abliterated-GGUF 1K
Same base model
DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF 40K mradermacher/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-i1-GGUF 2K mradermacher/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF 687 TrippyOG3/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF 498 alexgusevski/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-mlx-8Bit 357
Total size
143 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2025-06-07 12:33
Source huggingface.co/DevQuasar/DavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF ↗ Base model DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B →

Files by quantization

F16 1 file 34.3 GB
DavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B.f16.gguf 34.3 GB 0f2f16a7 download
Q8_0 1 file 18.2 GB
DavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B.Q8_0.gguf 18.2 GB beb2f8c0 download
Q6_K 1 file 14.1 GB
DavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B.Q6_K.gguf 14.1 GB 61999368 download
Q5_K 2 files 24.2 GB
DavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B.Q5_K_M.gguf 12.3 GB ce70f8bc download
DavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B.Q5_K_S.gguf 11.9 GB 10bd7510 download
Q4_K 2 files 20.5 GB
DavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B.Q4_K_M.gguf 10.5 GB 99d9ee90 download
DavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B.Q4_K_S.gguf 9.93 GB e649698c download
Q3_K 3 files 25.1 GB
DavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B.Q3_K_L.gguf 8.98 GB fb6abc1a download
DavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B.Q3_K_M.gguf 8.41 GB 19a00284 download
DavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B.Q3_K_S.gguf 7.69 GB 54d17644 download
Q2_K 1 file 6.56 GB
DavidAU.Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B.Q2_K.gguf 6.56 GB 693602b4 download
Auxiliary files 2 files 3.81 KB
.gitattributes 2.84 KB de6d51e7 download
README.md 991 B caa7fb92 download

README current version from Hugging Face

README history 1 version

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

  1. 2025-06-07Upload README.md with huggingface_hubb28ff20991 B
    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