Custom model for coding with agents to use locally with 16gb GPUs (working very fine...)
1,271 Pulls 1 Tag Updated 1 month ago
Code-targeted 184-of-256 expert cut of Qwen3.6-35B-A3B, LCB + MultiPL-E/HumanEval targeted, with MTP self-speculative decoding and vision tags. LCB v6 72.73 vs 61.04 base
579 Pulls 39 Tags Updated 1 week ago
A coding-optimized configuration of Qwen3.5-9B designed for 16 GB single-GPU hardware. The model uses the official Q4_K_M quantization (~6.6 GB weights), leaving ~9 GB headroom for KV cache — enabling 32K+ context windows comfortably.
954 Pulls 1 Tag Updated 2 months ago
Parable is Qwen3 fine-tuned on Claude Fable 5 and GPT-5.5 agent traces. Tool use, planning, and thinking for local agents. Sibling: Granite line at parable/granite4.1-fable.
729 Pulls 10 Tags Updated 1 month ago
Custom model for coding with agents to use locally with 24gb GPUs - BEST FOR OPENCODE!
1,007 Pulls 1 Tag Updated 1 month ago
Decensored Qwen2.5-3B-Instruct with 2/100 refusals via Heretic abliteration. General-purpose 3B model for local use.
1,666 Pulls 1 Tag Updated 1 month ago
Dolphin 3.0 Qwen 2.5 🐬 - A powerful, customizable AI model for local use.
3,436 Pulls 9 Tags Updated 1 year ago