Custom model for coding with agents to use locally with 16gb GPUs (working fine...)
56 Pulls 1 Tag Updated 14 hours ago
28.5K Pulls 1 Tag Updated 3 weeks ago
959 Pulls 1 Tag Updated 1 week ago
Qwen/Qwen3.6-27B + 3 Qwen3.6 fine-tunes with MLP-passthrough surgery - MTP quants
552 Pulls 8 Tags Updated 2 weeks ago
377 Pulls 1 Tag Updated 2 weeks ago
113 Pulls 1 Tag Updated 2 weeks ago
7,560 Pulls 5 Tags Updated 1 month ago
5,129 Pulls 1 Tag Updated 1 month ago
44 Pulls 1 Tag Updated 4 weeks ago
2,715 Pulls 1 Tag Updated 1 month ago
2,359 Pulls 3 Tags Updated 3 weeks ago
Qwen3.6-27B optimized for reverse engineering work in Ghidra.
31 Pulls 1 Tag Updated 3 weeks ago
22 Pulls 1 Tag Updated 2 weeks ago
Qwen3.6-27B uncensored by HauhauCS. I recently updated chat template so it generates tags more effectively
710 Pulls 1 Tag Updated 3 weeks ago
Qwen/Qwen3.6-27B + 3 Qwen3.6 fine-tunes with MLP-passthrough surgery
498 Pulls 27 Tags Updated 2 weeks ago
Qwen3.6-27B uncensored by HauhauCS. 0/465 Refusals. *
480 Pulls 1 Tag Updated 1 month ago
438 Pulls 1 Tag Updated 1 month ago
206 Pulls 1 Tag Updated 1 month ago
Qwen 3.6 Dense 27b
118 Pulls 1 Tag Updated 1 month ago
Qwen 3.6 Ollama profiles for RTX 5090 across 27B dense and 35B-A3B MoE variants, with vision, thinking mode, and native tool calling.
159 Pulls 3 Tags Updated yesterday