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

PocketWeights/Gliese-Qwen3.5-9B-Abliterated-WebGGUF

PocketWeights Qwen 9B GGUF multimodal second-order 262K 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/PocketWeights%2FGliese-Qwen3.5-9B-Abliterated-WebGGUF"
Response includes
  • classification m8
  • files 12
  • hub_downloads_all_time 313
  • author_summary 5 models
  • readme_text full
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
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
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
313
152 last 30d - stable
Likes
1
Model age
2mo ago
created 2026-08-04
Downloads over time
Now346→from82↑322%
6917027137282 on Aug 5346 on Oct 11AugSepOct
Aug 5 → Oct 11 · 50 snapshots · spans 67 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.

Metadata

License
apache-2.0
Quantizations
Q4 Q5
Tags
gguf quantized qwen3.5 vision image-captioning webllm webgpu abliterated uncensored pocketweights image-text-to-text base_model:prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption

Related

Total size
22.6 GB
Files
12
Quantizations
3
Registered
2026-08-22 13:56
Last updated on HF
2026-08-27 11:14

Files by quantization

Q5 2 files 12.2 GB
Gliese-Qwen3.5-9B-Abliterated-WebGGUF-Q5_1.gguf 6.33 GB 78b91a71 download
Gliese-Qwen3.5-9B-Abliterated-WebGGUF-Q5_0.gguf 5.87 GB 72f77fcf download
Q4 2 files 10.4 GB
Gliese-Qwen3.5-9B-Abliterated-WebGGUF-Q4_1.gguf 5.41 GB 470f65a1 download
Gliese-Qwen3.5-9B-Abliterated-WebGGUF-Q4_0.gguf 4.95 GB ec640446 download
Auxiliary files 8 files 8.83 KB
artifact-manifest.json 2.83 KB 3dbadde0 download
quantization-meta.json 2.15 KB 37b21458 download
.gitattributes 1.81 KB 58a367c9 download
README.md 1.59 KB 92cdce7e download
Gliese-Qwen3.5-9B-Abliterated-WebGGUF-Q4_0.gguf.sha256 114 B cfa20e98 download
Gliese-Qwen3.5-9B-Abliterated-WebGGUF-Q4_1.gguf.sha256 114 B a406f106 download
Gliese-Qwen3.5-9B-Abliterated-WebGGUF-Q5_0.gguf.sha256 114 B 2e9db4d4 download
Gliese-Qwen3.5-9B-Abliterated-WebGGUF-Q5_1.gguf.sha256 114 B 2dac2b75 download

README current version from Hugging Face


base_model: prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption
library_name: gguf
license: apache-2.0
tags:

  • gguf
  • qwen3.5
  • vision
  • webllm
  • webgpu

⚡ PocketWeights: Gliese-Qwen3.5-9B-Abliterated-WebGGUF

Heavy models, made light. We specialize in high-quality GGUF quantizations optimized for edge devices and gaming laptops.

What is this model?
This is an optimized GGUF of prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption. It is a highly capable 9B vision-language model, abliterated for unrestricted image captioning.

🌐 Why these specific formats? (WebGPU & Legacy Support)

While modern K-quants exist for this model, we explicitly generated these Q4_0 and Q5_0 files for developers building browser-based AI (WebLLM/WebGPU) and users on older hardware. These older formats offer maximum cross-platform compatibility where standard K-quants often fail or crash shaders.

📦 Pick Your Hardware

  • Q4_0: 🔥 Fits 6GB VRAM: The standard choice for WebLLM browser deployment. | Size: 4.9485 GiB
  • Q4_1: 🔥 Fits 6GB VRAM: The standard choice for WebLLM browser deployment. | Size: 5.4104 GiB
  • Q5_0: 💻 Fits 8GB VRAM: Higher precision for legacy AVX hardware. | Size: 5.8723 GiB
  • Q5_1: 💻 Fits 8GB VRAM: Higher precision for legacy AVX hardware. | Size: 6.3342 GiB

🚀 Quick Start (Ollama)

Run this model instantly in your terminal:

ollama run hf.co/PocketWeights/Gliese-Qwen3.5-9B-Abliterated-WebGGUF:Q4_0

README history 2 versions

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

  1. 2026-08-27Update README.md77a3eb95 KB
    Loading...
  2. 2026-08-04Add WebGGUF artifacts (Q4_0, Q4_1, Q5_0, Q5_1) @ 2026-08-04T10:41:05.217890+0...0bd42251.6 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.

Open in Abliteration