Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
15.7M Pulls 64 Tags Updated 1 month ago
Custom model for coding with agents to use locally with 16gb GPUs (working very fine...)
155 Pulls 1 Tag Updated 3 days ago
test
17 Pulls 2 Tags Updated 6 days ago
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.
11K Pulls 6 Tags Updated 3 weeks ago
1,985 Pulls 1 Tag Updated 3 weeks ago
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.
844 Pulls 6 Tags Updated 3 weeks ago
Abliterated (refusal-direction removed, Arditi et al. 2024) variant of `Qwen/Qwen3.5-4B`. **Not** fine-tuned — no preference/instruction data added; only the refusal direction is orthogonalized out.
547 Pulls 1 Tag Updated 4 weeks ago
Qwen3.5-35B-A3B-Base quantized to fit in 16GB GPU RAM
224 Pulls 2 Tags Updated 2 weeks ago
A balanced configuration variant of Qwen3.5-4B, planned for FIM (Fill-In-the-Middle) and Tool Calling in restrict capacity environments. Using the Q3_K_S GGUF quantization from HuggingFace (unsloth).
181 Pulls 2 Tags Updated 4 weeks ago
Havenlon-focused Qwen3.5 9B model for execution control, hardware trust boundaries, Web3 teams, and AI Agent execution risk.
95 Pulls 1 Tag Updated 2 weeks ago
26.3.7. Qwen3.5-9B-Q4 Update: This model introduces higher-quality reasoning trajectories across domains such as science, instruction-following, and mathematics.
24.3K Pulls 1 Tag Updated 4 months ago
Monolith GGUF of HauhauCS' Qwen3.5-Uncensored-Aggressive model family. With full vision support, patched model.
17.1K Pulls 3 Tags Updated 3 months ago
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.
14.7K Pulls 3 Tags Updated 4 months ago
Qwen3.5 Claude Coder — local coding agents A family of custom models built on **Qwen3.5**, tuned to act as **autonomous coding and administration agents**.
5,165 Pulls 2 Tags Updated 1 month ago
26.3.7. Qwen3.5-27B-Q4 Update: This model introduces higher-quality reasoning trajectories across domains such as science, instruction-following, and mathematics.
11.2K Pulls 1 Tag Updated 4 months ago
Qwopus3.5-v3 is a reasoning-enhanced model family fine-tune of Qwen3.5 designed to improve reasoning stability and correctness, optimize inference efficiency, and enhance cross-task generalization capabilities, especially in programming.
9,224 Pulls 7 Tags Updated 3 months ago
Coding-optimized variants of the official Qwen3.5 MoE models — full vision capability retained, tuned for precise code generation via lower temperature. Based on Alibaba's Qwen3.5 distributed through the Ollama registry.
10.3K Pulls 2 Tags Updated 4 months ago
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 +
4,285 Pulls 1 Tag Updated 1 month ago
6,915 Pulls 1 Tag Updated 3 months ago
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.
7,299 Pulls 1 Tag Updated 4 months ago