Qwen3 8B · Ollama

orcarouter/Qwen3.8-27B-Uncensored

Qwen3.8-27B tensor-level abliterated, vision tower and MTP head untouched. 0% over-refusal on XSTest, 0-6% refusal across the A/B suite, no measurable capability loss. Full mmproj vision, tool calling and thinking, 262K context.

vision tools thinking

29.4K Pulls 16 Tags Updated 5 days ago

tinyrick/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF

HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF

vision

213 Pulls 3 Tags Updated yesterday

jetelain/Qwen3.8-27B

Qwen3.8-27B UD-Q4_K_XL MTP from Unsloth

vision tools thinking

84 Pulls 1 Tag Updated 4 days ago

AI-TAVS/Qwen3.8-dau

Model exceeds all Qwen 3.8, 3.6 and 3.5 27B critical core benchmarks. A model that gets down to business faster, with less "talking" and is smarter too.

vision 27b

72 Pulls 3 Tags Updated 5 days ago

Havenlon/Execution-Boundary-Qwen38-27B-Q4_K_M

A Havenlon-focused Qwen3.8 27B model for execution-boundary reasoning, Adversarial Completeness, independent veto, evidence chains, and AI Agent execution control.

45 Pulls 1 Tag Updated 5 days ago

aiconjured/Qwen3.8-27B-NVFP4-MTP-COMPACT-LOW

Text + Vision All credit: https://huggingface.co/esatapedico/Qwen3.8-27B-NVFP4-MTP-GGUF

vision

30 Pulls 1 Tag Updated yesterday

Julioa/Qwen3.8-27B-UD-Q3_K_XL

24 Pulls 1 Tag Updated 14 hours ago

aiconjured/Qwen3.8-27B-NVFP4-MTP-VERY-HIGH

Text + Vision All credit: https://huggingface.co/esatapedico/Qwen3.8-27B-NVFP4-MTP-GGUF

vision

23 Pulls 1 Tag Updated yesterday

aiconjured/Qwen3.8-27B-NVFP4-MTP-MEDIUM

Text + Vision All credit: https://huggingface.co/esatapedico/Qwen3.8-27B-NVFP4-MTP-GGUF

vision

15 Pulls 1 Tag Updated yesterday

dna5rm/qwen3.8

Qwen3.8-27B Q4_K_M, default context 131072, tuned for a 32 GB NVIDIA RTX 5090.

vision tools thinking

15 Pulls 1 Tag Updated 3 days ago

aiconjured/Qwen3.8-27B-NVFP4-MTP-VERY-LOW

Text + Vision All credit: https://huggingface.co/esatapedico/Qwen3.8-27B-NVFP4-MTP-GGUF

vision

12 Pulls 1 Tag Updated yesterday

aiconjured/Qwen3.8-27B-NVFP4-MTP-LOW

Text + Vision All credit: https://huggingface.co/esatapedico/Qwen3.8-27B-NVFP4-MTP-GGUF

vision

7 Pulls 1 Tag Updated yesterday

aiconjured/Qwen3.8-27B-NVFP4-MTP-MID-HIGH

Text + Vision All credit: https://huggingface.co/esatapedico/Qwen3.8-27B-NVFP4-MTP-GGUF

vision

5 Pulls 1 Tag Updated yesterday

smtek/Qwen3.8-27B

Quants from Q2 up to Q5 from Unsloth K_M and UD_K_XL and builds for 12, 16 and 24 GB

vision

8,923 Pulls 22 Tags Updated 2 days ago

Distendo/zen-pro

Zen Pro (flagship model) — an uncensored, human-like AI built on Qwen3 8B. It's like a real AI, not a corporate and not a stupid chatbot.

tools thinking

11.9K Pulls 1 Tag Updated 3 weeks ago

jikepjikep_16HEX/qwen3.8-27b-nightshift-heretic-uncensored-q4

😈 Uncensored Qwen3.8-27B Vision (27.3B • Q4_K_M) for Ollama. 👁️ Multimodal Vision AI with CLIP-ViT, Thinking, MTP, Tool Calling, Rust 1.98.0 Image Analysis, GGUF & local AI development. Medic🚀 #16HEX Matrix / Nightshift Heretic.

vision

1,521 Pulls 1 Tag Updated yesterday

ttempvnn/0bserverx-Qwen3.8-27B-Heretic-Abliterated-Uncensored-Q4-K-M

1,087 Pulls 1 Tag Updated 1 week ago

oamazonasgabriel/qwen3.8-27b

Qwen3.8-27B in Q4_K_M quantization (32GB+ VRAM required). Dense 27.8B parameters with hybrid attention for long context (256K tokens). Apache 2.0 license. Ideal for high-VRAM setups (RTX 5090/4090 dual, M4 Ultra, etc.).

586 Pulls 1 Tag Updated 1 week ago

zhamm/Qwen3.8

High-quality Q8_0 quantization of Qwen3.8-27B packaged for Ollama with full vision support and MTP for speed.

vision

506 Pulls 1 Tag Updated 4 days ago

ttempvnn/Blackfrost-AI-Qwen3.8-27B-ABLITERATED

vision

312 Pulls 1 Tag Updated 1 week ago