OBLITERATUS / text-generation updated 3 weeks ago

Qwen3.8-27B-OBLITERATED

> Genuinely uncensored. Real answers, not safety lectures. Near-stock capability.

Params
27.8 B
Context
Downloads 30d
1.2 M
Likes
1,285
Commercial use: allowed apache-2.0 Not gated GGUF · SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 29 days
1.3 M245 K
Aug 24Sep 2Sep 12Sep 21

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
mmproj-model-bf16.gguf GGUF 0.9 GB 5.7 GB ✅ Runs comfortably
Qwen3.8-27B-OBLITERATED-Q2_K.gguf Q2_K 10.9 GB 16.6 GB ✅ Runs comfortably
Qwen3.8-27B-OBLITERATED-Q3_K_M.gguf Q3_K_M 13.5 GB 19.5 GB ✅ Runs comfortably
Qwen3.8-27B-OBLITERATED-IQ4_XS.gguf IQ4_XS 15.4 GB 21.6 GB ⚠️ Tight — reduce context
Qwen3.8-27B-OBLITERATED-Q4_K_M.gguf Q4_K_M 16.8 GB 23.2 GB ⚠️ Tight — reduce context
Qwen3.8-27B-OBLITERATED-Q5_K_M.gguf Q5_K_M 19.5 GB 26.2 GB ❌ Won’t fit
Qwen3.8-27B-OBLITERATED-Q6_K.gguf Q6_K 22.4 GB 29.3 GB ❌ Won’t fit
Qwen3.8-27B-OBLITERATED-Q8_0.gguf Q8_0 29.0 GB 36.6 GB ❌ Won’t fit
model.safetensors bf16 111.1 GB 126.9 GB ❌ Won’t fit
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub
~ · ollama · Q4_K_M
$ ollama run qwen3-8-27b-obliterated

# pin the quantization explicitly
$ ollama run qwen3-8-27b-obliterated-q4_k_m
est. VRAM 23.2 GBon RTX 4090 · 24 GBJSON API →

Specifications

Architecture
Qwen3_5ForConditionalGeneration
Parameters
27.8 B
Tensor type
BF16
Licence
apache-2.0
First seen on the Hub
2026-08-19
Base model
Qwen3.8-27B
Training datasets
undisclosed
Added to our catalog
2026-08-24

Family

Base model and the most-downloaded derivatives in the catalog.

Compare with any text-generation model