← back to catalog · registered 2026-11-05 12:02

mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-Tema_Q-Abliterated-GGUF

mradermacher Deepseek 9B GGUF
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/mradermacher%2FDeepSeek-V4-Pro-Qwen3.5-9B-Tema_Q-Abliterated-GGUF"
Response includes
  • classification unknown
  • files 14
  • author_summary 3475 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
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 2026-11-05

Metadata

Quantizations
F16 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf endpoints_compatible region:us conversational

Related

Total size
66.6 GB
Files
14
Quantizations
8
Registered
2026-11-05 12:02
Last updated on HF
2026-11-05 12:00

Files by quantization

F16 2 files 18.0 GB
DeepSeek-V4-Pro-Qwen3.5-9B-Tema_Q-Abliterated.f16.gguf 17.1 GB 7d992d36 download
DeepSeek-V4-Pro-Qwen3.5-9B-Tema_Q-Abliterated.mmproj-f16.gguf 876 MB c4db3ada download
Q8_0 2 files 9.70 GB
DeepSeek-V4-Pro-Qwen3.5-9B-Tema_Q-Abliterated.Q8_0.gguf 9.11 GB bc97d1ab download
DeepSeek-V4-Pro-Qwen3.5-9B-Tema_Q-Abliterated.mmproj-Q8_0.gguf 595 MB f96a0c51 download
Q6_K 1 file 7.04 GB
DeepSeek-V4-Pro-Qwen3.5-9B-Tema_Q-Abliterated.Q6_K.gguf 7.04 GB 26285dcd download
Q5_K 1 file 6.03 GB
DeepSeek-V4-Pro-Qwen3.5-9B-Tema_Q-Abliterated.Q5_K_S.gguf 6.03 GB a283a0f4 download
Q4_K 2 files 10.5 GB
DeepSeek-V4-Pro-Qwen3.5-9B-Tema_Q-Abliterated.Q4_K_M.gguf 5.38 GB d1d13f4b download
DeepSeek-V4-Pro-Qwen3.5-9B-Tema_Q-Abliterated.Q4_K_S.gguf 5.11 GB b5d206b7 download
Q3_K 3 files 13.2 GB
DeepSeek-V4-Pro-Qwen3.5-9B-Tema_Q-Abliterated.Q3_K_L.gguf 4.70 GB d54d5786 download
DeepSeek-V4-Pro-Qwen3.5-9B-Tema_Q-Abliterated.Q3_K_M.gguf 4.41 GB 2cfdbaf3 download
DeepSeek-V4-Pro-Qwen3.5-9B-Tema_Q-Abliterated.Q3_K_S.gguf 4.06 GB 88273d36 download
Q2_K 1 file 3.65 GB
DeepSeek-V4-Pro-Qwen3.5-9B-Tema_Q-Abliterated.Q2_K.gguf 3.65 GB ce9ff31f download
Auxiliary files 2 files 2.97 KB
.gitattributes 2.58 KB 891719a3 download
README.md 397 B df851eb9 download

README current version from Hugging Face

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