20+ models
Nex-N2.5-mini (nex-agi) : MoE 35B / ~3B actifs post-trained on Qwen3.5-35B-A3B. Vision, tool-calling, reasoning, 256k context. Quants Q5_K_M, Q4_K_M (latest), Q3_K_M, Q2_K.
Qwen3.5-35B-A3B-Base quantized to fit in 16GB GPU RAM
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled is a highly capable reasoning model fine-tuned on top of the powerful Qwen3.5 architecture. The model's core directive is to leverage state-of-the-art Chain-of-Thought (CoT) distillation primarily source
A text-only, thinking-capable variant of Qwen3.5-35B-A3B — leaner and faster by removing the CLIP vision projector. Based on Unsloth's Q4_K_M quantization of Alibaba's Qwen3.5-35B-A3B.
unsloth qwen 3.5 with thinking disabled
Qwen3.5-35B-A3B APEX GGUF -- A Novel MoE-Aware Mixed-Precision Quantization Technique Brought to you by the LocalAI team -- the creators of LocalAI the open-source AI engine that runs any model - LLMs, vision, image - on any hardware.
A Havenlon-focused Qwen AgentWorld 35B-A3B model for local agent-environment simulation, next-state prediction, execution consequence reasoning, and controlled real-world AI research.
Mixed-precision quant of Qwen3.6-35B-A3B: 8-bit attention, 4-bit experts.
Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-fulluncen
A custom model built on Qwen3.6-35B-A3B (abliterated), tuned to act as an autonomous coding and administration agent. It speaks the Anthropic-compatible API, so it drives Claude Code fully locally — your code never leaves your machine.
llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-GGUF with Vision
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive IQ3_M量化GGUF私有模型(破解)
APEX model from Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled
Qwen3.6-35B-A3B uncensored by HauhauCS. 0/465 Refusals. Patched to have vision support; Fully functional, 100% of what the original authors intended - just without the refusals. These are meant to be the best lossless uncensored models out there.
Q4-K-M based on lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled
APEX (Adaptive Precision for EXpert Models) quantizations of Qwen/Qwen3.6-35B-A3B, to try to optimize performance.
Qwen 3.8 distilled into Qwen 3.6 35B-A3B
A memory-efficient model configuration of Qwen3.6-35B-A3B using an upstream imatrix-calibrated IQ4_XS quantization and q4_0 KV cache. Designed for 24 GB VRAM
Qwen 3.6 Ollama profiles for RTX 5090 across 27B dense and 35B-A3B MoE variants, with vision, thinking mode, and native tool calling.