Qwen3.5 9b · Ollama

Fine-tuned Qwen3.5-9B with distilled reasoning and full vision support. 883 tensors — vision tower preserved byte-for-byte from base. R5 was the first vision-capable distilled model.

vision tools thinking

301 Pulls 1 Tag Updated 2 weeks ago

robit/qwen3.5-9b-r7-research-vision

Fine-tuned Qwen3.5-9B with distilled reasoning and full vision support. 883 tensors (427 text + 441 vision + 15 MTP) — vision tower preserved byte-for-byte from base via llama-export-lora merge.

vision tools thinking

234 Pulls 1 Tag Updated 2 weeks ago

kwangsuklee/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

26.3.7. Qwen3.5-9B-Q4 Update: This model introduces higher-quality reasoning trajectories across domains such as science, instruction-following, and mathematics.

22.2K Pulls 1 Tag Updated 1 month ago

robit/qwen3.5-9b-r7-research

Fine-tuned Qwen3.5-9B with distilled reasoning from research-backed datasets. Trained via LoRA SFT with an additive data strategy that preserves base model capabilities while improving instruction following and reasoning.

tools thinking

65 Pulls 1 Tag Updated 2 weeks ago

carstenuhlig/omnicoder-9b

9B coding agent based on Qwen3.5-9B, fine-tuned on 425K real agentic traces from Claude Opus 4.6, GPT-5.4, and Gemini 3.1. Reads before it writes, traces bugs to the root cause, doesn't clobber your existing code.

tools thinking

10K Pulls 3 Tags Updated 1 month ago

lukey03/qwen3.5-9b-abliterated-vision

vision tools thinking

11.6K Pulls 1 Tag Updated 1 month ago

zfujicute/OmniCoder-Qwen3.5-9B-Claude-4.6-Opus-Uncensored-v2-GGUF

5,130 Pulls 1 Tag Updated 1 month ago

kwangsuklee/Qwen3.5-9B.Q4_K_M-Claude-4.6-Opus-Reasoning-Distilled-v2

26.3.18. Ver.2 update: This iteration is powered by 14,000+ premium Claude 4.6 Opus-style general reasoning samples, with a major focus on achieving massive gains in reasoning efficiency while actively improving peak accuracy.

5,976 Pulls 1 Tag Updated 1 month ago

carstenuhlig/omnicoder-2-9b

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. Original: https://hf.co/Tesslate/OmniCoder-2-9B

tools thinking

3,119 Pulls 2 Tags Updated 1 month ago

lukey03/qwen3.5-9b-abliterated

tools thinking

4,333 Pulls 1 Tag Updated 1 month ago

robit/qwen3.5-9b-r5-research

Fine-tuned Qwen3.5-9B with distilled reasoning from research-backed datasets. R5 was the first round to use production-quality data sources (Bespoke-Stratos, Tulu-3, SlimOrca) and achieved 84.2% on diverse eval — surpassing the base model.

tools thinking

20 Pulls 1 Tag Updated 2 weeks ago