20+ models
Text-only Qwen3.5 9B GGUF files. Default: q4_k_m. TurinTech models, built with Artemis.
The foundational weights of Qwen/Qwen3.5-9B with selected specialization to maximize coding + agentic work at a small size using distillation/donar weights. ~7 GB loaded. Q4_K_M.
MiMo-V2.6-Distill-9B (Qwen3.5-9B SFT): coding, agent tasks, visual coding, cybersecurity. Thinking + instruct quants, multimodal.
Huihui Qwen3.5 9B abliterated, GGUF Q4_K_M. A standalone release packaged by Interim Labs.
Abliterated build of Qwythos-9B-Claude-Mythos, a Claude-style creative & reasoning model (Qwen3.5-9B base) with refusals further reduced via the Heretic library.
Qwen3.5 9B in GGUF Q4_K_M, packaged by Interim Labs for local text generation.
Text + Vision Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-MTP-GGUF-NVFP4
Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF
Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash - is an efficient reasoning model distilled using high-quality data from DeepSeek-V4. + vision. ollama v.0.30.0-rc20 +
pull from hf.co/Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF
Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash - is an efficient reasoning model distilled using high-quality data from DeepSeek-V4.
Custom model for coding with agents to use locally with 16gb GPUs (working very fine...)
Jev V2 Only Better its Bev, your drunk girlfriend: a decision model (Qwen3.5-9B base) trained to be confidently WRONG. 98% wrong, 96% sure. A joke, not advice.
Abliterated build of Qwable-9B-Claude-Fable, a Claude-style creative and reasoning model (Qwen3.5-9B base) with refusals reduced via the Heretic library.
Qwen3.5-9B-Red_Team is a fine-tuned version of Qwen3.5-9B, specifically optimized for offensive cybersecurity operations, adversary simulation, and Red Teaming tactics.
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.
Four-way omnimerge_v2 over Qwen3.5-9B (DeltaCoder 0.55 / Qwopus 0.30 / Ornith 0.15), built for multi-turn agentic coding: it keeps a task moving across turns and tool calls instead of re-issuing the same call. 9B dense, MTP head
2nd gen OmniCoder, fine-tuned from Qwen3.5-9B. Trains on assistant tokens only (unlike v1): no more repetition loops, stable tool-calling in long agentic sessions. With a better prompt in general.