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

featherless-ai-quants/huihui-ai-Qwen2.5-14B-Instruct-abliterated-GGUF

featherless-ai-quants Qwen 14B GGUF second-order 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/featherless-ai-quants%2Fhuihui-ai-Qwen2.5-14B-Instruct-abliterated-GGUF"
Response includes
  • classification m8
  • files 14
  • hub_downloads_all_time 4,169
  • author_summary 73 models
  • readme_text full
Try next
GET/models?author=featherless-ai-quants
All 73 models by featherless-ai-quants
 GET/models?family=qwen&method=m8
Sibling qwen 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
4K
1K last 30d - stable
Likes
1
Model age
19mo ago
created 2025-03-11
Downloads over time
Now4.5K→from0↑0%
01.7K3.3K5K0 on Mar 5, 20254.5K on Oct 12Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 5, 2025 → Oct 12 · 124 snapshots · spans 586 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.

huihui-ai/Qwen2.5-14B-Instruct-abliterated this lineage
featherless-ai-quants/huihui-ai-Qwen2.5-14B-Instruct-abliterated-GGUF↓ 1,047

Metadata

Quantizations
IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf text-generation endpoints_compatible region:us conversational

Related

Other by featherless-ai-quants
huihui-ai-Qwen2.5-7B-Instruct-abliterated-GGUF 2K informatiker-Qwen2-7B-Instruct-abliterated-GGUF 1K huihui-ai-Qwen2.5-Coder-7B-Instruct-abliterated-GGUF 1K grimjim-Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF 1K ModelsLab-Llama-3.1-8b-Uncensored-Dare-GGUF 1K
Same base model
mradermacher/Qwen2.5-14B-Instruct-abliterated-GGUF 16K mradermacher/Qwen2.5-14B-Instruct-abliterated-i1-GGUF 3K cgus/Qwen2.5-14B-Instruct-abliterated-exl2 26
Total size
95.0 GB
Files
14
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2025-03-11 22:28
Source huggingface.co/featherless-ai-quants/huihui-ai-Qwen2.5-14B-Instruct-abliterated-GGUF ↗ Base model huihui-ai/Qwen2.5-14B-Instruct-abliterated ↗

Files by quantization

Q8_0 1 file 14.6 GB
huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q8_0.gguf 14.6 GB bd60ea75 download
Q6_K 1 file 11.3 GB
huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q6_K.gguf 11.3 GB ae1e8704 download
Q5_K 2 files 19.3 GB
huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q5_K_M.gguf 9.79 GB 094d769f download
huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q5_K_S.gguf 9.56 GB f2571f3f download
Q4_K 2 files 16.4 GB
huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q4_K_M.gguf 8.37 GB 1c354d92 download
huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q4_K_S.gguf 7.98 GB a695a1ef download
IQ4 1 file 7.62 GB
huihui-ai-Qwen2.5-14B-Instruct-abliterated-IQ4_XS.gguf 7.62 GB 4977e31a download
Q3_K 3 files 20.4 GB
huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q3_K_L.gguf 7.38 GB 186817f4 download
huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q3_K_M.gguf 6.84 GB f2755e3f download
huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q3_K_S.gguf 6.20 GB 5a8af195 download
Q2_K 1 file 5.37 GB
huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q2_K.gguf 5.37 GB 376ab7a2 download
Auxiliary files 3 files 1.55 MB
featherless-quants.png 1.54 MB 2e1b4d66 download
README.md 3.61 KB f9fdb7fb download
.gitattributes 2.51 KB 78b7db99 download

README current version from Hugging Face

base_model: huihui-ai/Qwen2.5-14B-Instruct-abliterated
pipeline_tag: text-generation
quantized_by: featherless-ai-quants

huihui-ai/Qwen2.5-14B-Instruct-abliterated GGUF Quantizations 🚀

Featherless AI Quants

Optimized GGUF quantization files for enhanced model performance

Powered by Featherless AI - run any model you'd like for a simple small fee.

Available Quantizations 📊

Quantization Type File Size
IQ4_XS huihui-ai-Qwen2.5-14B-Instruct-abliterated-IQ4_XS.gguf 7806.96 MB
Q2_K huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q2_K.gguf 5503.18 MB
Q3_K_L huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q3_K_L.gguf 7557.65 MB
Q3_K_M huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q3_K_M.gguf 6999.21 MB
Q3_K_S huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q3_K_S.gguf 6351.09 MB
Q4_K_M huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q4_K_M.gguf 8571.73 MB
Q4_K_S huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q4_K_S.gguf 8176.26 MB
Q5_K_M huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q5_K_M.gguf 10022.04 MB
Q5_K_S huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q5_K_S.gguf 9790.95 MB
Q6_K huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q6_K.gguf 11563.00 MB
Q8_0 huihui-ai-Qwen2.5-14B-Instruct-abliterated-Q8_0.gguf 14974.21 MB

⚡ Powered by Featherless AI

Key Features

  • 🔥 Instant Hosting - Deploy any Llama model on HuggingFace instantly
  • 🛠️ Zero Infrastructure - No server setup or maintenance required
  • 📚 Vast Compatibility - Support for 2400+ models and counting
  • 💎 Affordable Pricing - Starting at just $10/month

Links:
Get Started | Documentation | Models

README history 1 version

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

  1. 2025-03-11Upload folder using huggingface_hubed48fef3.6 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