Get the app
← back to catalog · registered 2026-11-01 13:01

tinyopsec/DeepSeek-R1-Distill-Qwen-1.5B-abliterated-GGUF

tinyopsec Qwen 1.5B GGUF second-order
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/tinyopsec%2FDeepSeek-R1-Distill-Qwen-1.5B-abliterated-GGUF"
Response includes
  • classification m8
  • files 15
  • author_summary 11 models
  • readme_text full
Try next
GET/models?author=tinyopsec
All 11 models by tinyopsec
 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 · 30-day
0
Likes
0
Model age
today
created 2026-11-01

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/DeepSeek-R1-Distill-Qwen-1.5B-abliterated↓ 492 this lineage
tinyopsec/DeepSeek-R1-Distill-Qwen-1.5B-abliterated-GGUF

Metadata

License
mit
Quantizations
F16 Q2_K Q3_K Q4 Q4_K Q5 Q5_K Q6_K Q8_0
Tags
gguf qwen2 quantized text-generation base_model:huihui-ai/DeepSeek-R1-Distill-Qwen-1.5B-abliterated base_model:quantized:huihui-ai/DeepSeek-R1-Distill-Qwen-1.5B-abliterated license:mit endpoints_compatible region:us conversational

Related

Other by tinyopsec
Qwen3.5-4B-Uncensored-Aggressive-GGUF 2K Llama-3.2-3B-Instruct-heretic-ablitered-uncensored-GGUF 1K Huihui-MiniCPM5-2B-abliterated-GGUF 809 MiniCPM5-2B-Abliterated-Uncensored-Safetensors-GGUF 651 MiniCPM5-1B-Uncensored-GGUF 450
Same base model
mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-abliterated-GGUF 3K mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-abliterated-i1-GGUF 710
Total size
16.3 GB
Files
15
Quantizations
10
Registered
2026-11-01 13:01
Last updated on HF
2026-11-01 12:59
Source huggingface.co/tinyopsec/DeepSeek-R1-Distill-Qwen-1.5B-abliterated-GGUF ↗ Base model huihui-ai/DeepSeek-R1-Distill-Qwen-1.5B-abliterated →

Files by quantization

F16 1 file 3.32 GB
model-F16.gguf 3.32 GB ecc52c2c download
Q8_0 1 file 1.76 GB
model-Q8_0.gguf 1.76 GB feef6f59 download
Q6_K 1 file 1.36 GB
model-Q6_K.gguf 1.36 GB 4f13a0ca download
Q5_K 2 files 2.37 GB
model-Q5_K_M.gguf 1.20 GB f7dcf2df download
model-Q5_K_S.gguf 1.17 GB 334225fa download
Q5 1 file 1.17 GB
model-Q5_0.gguf 1.17 GB 729a6118 download
Q4_K 2 files 2.04 GB
model-Q4_K_M.gguf 1.04 GB f9ea2e64 download
model-Q4_K_S.gguf 1022 MB dccae2f2 download
Q4 1 file 1017 MB
model-Q4_0.gguf 1017 MB b9776590 download
Q3_K 3 files 2.58 GB
model-Q3_K_L.gguf 935 MB 20ec771a download
model-Q3_K_M.gguf 882 MB f094a8ed download
model-Q3_K_S.gguf 821 MB dde42bbc download
Q2_K 1 file 718 MB
model-Q2_K.gguf 718 MB 590dcf57 download
Auxiliary files 2 files 3.14 KB
.gitattributes 2.16 KB 69701adf download
README.md 1007 B 590aa863 download

README current version from Hugging Face

license: mit
base_model: huihui-ai/DeepSeek-R1-Distill-Qwen-1.5B-abliterated
base_model_relation: quantized
library_name: gguf
pipeline_tag: text-generation
tags:

  • gguf
  • qwen2
  • quantized

DeepSeek-R1-Distill-Qwen-1.5B-abliterated - GGUF

GGUF quantizations of huihui-ai/DeepSeek-R1-Distill-Qwen-1.5B-abliterated, produced with llama.cpp.

Available files

File Quantization
model-F16.gguf F16
model-Q8_0.gguf Q8_0
model-Q6_K.gguf Q6_K
model-Q5_K_M.gguf Q5_K_M
model-Q5_K_S.gguf Q5_K_S
model-Q5_0.gguf Q5_0
model-Q4_K_M.gguf Q4_K_M
model-Q4_K_S.gguf Q4_K_S
model-Q4_0.gguf Q4_0
model-Q3_K_L.gguf Q3_K_L
model-Q3_K_M.gguf Q3_K_M
model-Q3_K_S.gguf Q3_K_S
model-Q2_K.gguf Q2_K

Usage

With llama.cpp:

./llama-cli -m model-Q4_K_M.gguf -p "Your prompt" -n 256

License

MIT, inherited from the base model.

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