JonathanColetti / text-generation updated 3 weeks ago

Qwen3.8-27B-Uncensored-GGUF

Uncensored Qwen3.8-27B, published as GGUF quantizations with the multi token prediction (MTP) head retained and verified.

Params
Context
Downloads 30d
2.3 M
Likes
1,165
Commercial use: allowed apache-2.0 Not gated GGUF 2 languages View on Hugging Face ↗

Download history

daily snapshots · 35 days
▲ 1.3 M in the last 30 days (134.9%)
3.0 M184 K
Aug 17Aug 28Sep 9Sep 20

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-Qwen3.8-27B-Uncensored-F16.gguf GGUF 0.9 GB 1.5 GB ✅ Runs comfortably
Qwen3.8-27B-Uncensored-draft-Q4_0.gguf Q4_0 1.7 GB 2.3 GB ✅ Runs comfortably
Qwen3.8-27B-Uncensored-IQ2_M.gguf IQ2_M 10.6 GB 12.2 GB ✅ Runs comfortably
Qwen3.8-27B-Uncensored-IQ4_XS.gguf IQ4_XS 15.3 GB 17.3 GB ✅ Runs comfortably
Qwen3.8-27B-Uncensored-Q4_K_M.gguf Q4_K_M 16.8 GB 19.0 GB ✅ Runs comfortably
Qwen3.8-27B-Uncensored-Q5_K_M.gguf Q5_K_M 19.5 GB 22.0 GB ⚠️ Tight — reduce context
Qwen3.8-27B-Uncensored-Q6_K.gguf Q6_K 22.4 GB 25.2 GB ❌ Won’t fit
Qwen3.8-27B-Uncensored-Q8_0.gguf Q8_0 29.0 GB 32.5 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-uncensored-gguf

# pin the quantization explicitly
$ ollama run qwen3-8-27b-uncensored-gguf-q4_k_m
est. VRAM 19.0 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
apache-2.0
First seen on the Hub
2026-08-14
Base model
Qwen3.8-27B
Training datasets
undisclosed
Added to our catalog
2026-08-17

Family

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

Compare with any text-generation model