qwen3.5

Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.

vision tools thinking cloud 0.8b 2b 4b 9b 27b 35b 122b

15.7M Pulls 64 Tags Updated 1 month ago

aratan/Qwythos-9B-v2-1M-Uncensored-GGUF

Contexto de 1 Millon, Sin censura y basado en qwen3.5

vision

212 Pulls 1 Tag Updated 3 days ago

edtorre/qwen3.5-hermes

A compact, agent-tuned Qwen 3.5 model built for local agent harnesses like Hermes Agent. Based on `qwen3.5:latest` with Q4_K_M quantization for a lightweight 6.6 GB footprint, while retaining strong tool-calling, vision, and thinking capabilities.

vision tools thinking

255 Pulls 1 Tag Updated 5 days ago

SetneufPT/Qwen3.5-9B-Coder_Q4_256k_ABL_16GB-GPU

Custom model for coding with agents to use locally with 16gb GPUs (working very fine...)

vision tools thinking

155 Pulls 1 Tag Updated 3 days ago

aratan/Qwythos-9B-Claude-Mythos-5-1M-GGUF

basado en qwen3.5, con 1 Millon de contexto + Entrenado con datos de Mythos Para codigo y razonamiento

vision

85 Pulls 1 Tag Updated 3 days ago

nutboy02/Qwen35B-Agent-R2

test

17 Pulls 2 Tags Updated 6 days ago

naseemap47/qwen3.5-4b-yolo

6 Pulls 1 Tag Updated 5 days ago

richardyoung/qwythos-9b-abliterated

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.

10.9K Pulls 6 Tags Updated 3 weeks ago

dzgg/Qwen3.5-Uncensored-HauhauCS-Aggressive

vision tools thinking 4b

1,983 Pulls 1 Tag Updated 3 weeks ago

richardyoung/qwable-9b-abliterated

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

lileilei999/qwen3.5-9b-abliterated-vision

vision

373 Pulls 1 Tag Updated 1 week ago

kaineone/qwen3.5-4b-abliterated

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

HammerAI/qwen3.5-abliterated

huihui_ai/qwen3.5-abliterated

vision tools thinking

324 Pulls 2 Tags Updated 2 weeks ago

Kunj0195/qwen3.5-coder

238 Pulls 1 Tag Updated 2 weeks ago

maxwellb/Qwen3.5-35B-A3B-Base

Qwen3.5-35B-A3B-Base quantized to fit in 16GB GPU RAM

vision tools thinking

224 Pulls 2 Tags Updated 2 weeks ago

huihui_ai/qwen3.5-abliterated

Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.

vision tools thinking 0.8b 2b 4b 9b 27b 35b 122b

421.9K Pulls 58 Tags Updated 3 months ago

dzgg/qwen3.5-abliterated

vision tools thinking 4b

177 Pulls 1 Tag Updated 3 weeks ago

oamazonasgabriel/qwen3.5-4b

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

oamazonasgabriel/qwen3.5-2b-mlx

Compact 1.9B language model in BF16 precision, optimized for MLX workflows. Features thinking/reasoning mode, tool calling, and a massive 262K token context window. Runs on GPUs with 8 GB+ memory.

95 Pulls 1 Tag Updated 1 week ago

Havenlon/Havenlon-Qwen35-9B-Q4_K_M

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