Qwen3 Max · Ollama

mdq100/qwen3.5

Custom Qwen3.5 variants optimized for 128GB unified memory systems, such as AMD Ryzen AI Max+ 395. On Windows 11, GPU is limited to 96GB (32GB reserved for OS/CPU), requiring context window capped at 131072 tokens (128K) to fit within GPU memory limits.

vision tools thinking

431 Pulls 2 Tags Updated 5 months ago

srchmnmichael/qwen3.5-9B-uncensored

Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

1,018 Pulls 4 Tags Updated 4 days ago

tinyrick/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-Vision

vision

2,255 Pulls 1 Tag Updated 4 weeks ago

n0404n0404/qwen3.6-finetune-qwen3.8-max-glm5.2-kimi-k3-distillation-a56-1168cb-heretic

567 Pulls 4 Tags Updated 3 weeks ago

edtorre/qwen3.6-hermes

Qwen 3.6 27B (Q4_K_M) optimized for Hermes Agent — 64K context, 8192 max tokens, MTP for speed, flash attention + Q8 KV cache.

vision tools thinking

810 Pulls 1 Tag Updated 1 month ago

Omoeba/qwen3-coder-max

maximum 256k context length by default

tools 30b

1,535 Pulls 1 Tag Updated 11 months ago

Omoeba/qwen3-2507-abliterated-max

maximum 256k context length for coding and other long-context tasks

tools 30b

871 Pulls 1 Tag Updated 11 months ago

aware/qwen3.6-40b-deck-opus-neo-code

DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-NEO-CODE-Di-IMatrix-MAX-GGUF

1,733 Pulls 1 Tag Updated 3 months ago

zdolny/qwen3-coder58k-tools

qwen3-coder with tools calling, context 58k to match full memory 31GB on RTX5090

tools

586 Pulls 1 Tag Updated 1 year ago

joachimhansen/opencode-qwen3

Made for a rig with TRX 3080 10Gb, 32gb RAM and Ryzen 5800x

tools

31 Pulls 1 Tag Updated 2 months ago

S00K/alice

Alice is a roleplay LLM based on qwen3:4b-instruct-2507-q4_K_M, simulating Alice Marie Chen, a 20yo from Portland. Features an 8k context window and is optimized for WhatsApp. The persona is an anti-assistant with a texting style, refusing technical tasks

tools thinking

705 Pulls 1 Tag Updated 7 months ago

lucloner/wen36-35b-uncensored-1m

Qwen3.6-35B-A3B Uncensored is a Mixture-of-Experts model with 35.5B total parameters and 3B activated, extended to 1M-token context with the official MTP speculative-decoding layer, delivering 1.5x decode speedup on Ollama, with native thinking and tools.

tools thinking

347 Pulls 2 Tags Updated 2 weeks ago

rafw007/qwen36-a3b-claude-coder

Qwen3.6-35B-A3B MoE coding agent for Claude Code / Codex / opencode, 64K context, native tool-calling, honest tool use, safety guardrails intact

vision tools thinking

3,559 Pulls 2 Tags Updated 2 months ago

Havenlon/Execution-Boundary-Qwen35-27B-Q4_K_M

A Havenlon-focused Qwen3.5 27B model for deep reasoning about execution boundaries, Adversarial Completeness, AI Agent control, evidence chains, and real-world execution.

2 Pulls 3 Tags Updated 1 week ago

ExpedientFalcon/qwen3-14b-agent-m2max

tools thinking

96 Pulls 1 Tag Updated 1 year ago

srchmnmichael/Qwen3.8-Uncensored

Qwen3.8-27B tensor-level abliterated, vision tower and MTP head untouched. 0% over-refusal on XSTest, 0-6% refusal across the A/B suite, no measurable capability loss. Full mmproj vision, tool calling and thinking, 262K context.

vision tools thinking

2,064 Pulls 4 Tags Updated 4 days ago

orcarouter/Qwen3.8-27B-Uncensored

Qwen3.8-27B tensor-level abliterated, vision tower and MTP head untouched. 0% over-refusal on XSTest, 0-6% refusal across the A/B suite, no measurable capability loss. Full mmproj vision, tool calling and thinking, 262K context.

vision tools thinking

129.6K Pulls 20 Tags Updated 4 days ago

oamazonasgabriel/qwen3.6-35b-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

tools thinking

2,022 Pulls 1 Tag Updated 2 months ago

fredrezones55/Qwen3.5-APEX

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.

vision tools thinking

755 Pulls 2 Tags Updated 4 months ago

Maternion/manim-coder

Fine-tuned manim model using Qwen2.5-Coder-14B-Instruct trained on 3blue1brown-manim dataset with 2,407 examples.

tools 14b

541 Pulls 3 Tags Updated 6 months ago