OpenReasoner is a fine-tuned qwen3:8b and qwen3:1.7b model trained on the OpenThoughts-114k dataset.
184 Pulls 2 Tags Updated 6 months ago
Renamed qwen3:14b
173 Pulls 1 Tag Updated 11 months ago
Renamed qwen3:1.7b.
58 Pulls 1 Tag Updated 11 months ago
18 Pulls 1 Tag Updated 7 months ago
Qwen3.8-Flash-Next tensor-level abliterated— a latest Qwen4-architecture MoE (~177B total / ~6B active) with vision, reasoning, tool-calling, and 262K context. MLX 4/6/8-bit for Apple Silicon. Research use only.
1,990 Pulls 4 Tags Updated 4 days ago
Quants from Q2 up to Q5 from Unsloth K_M and UD_K_XL and builds for 12, 16 and 24 GB
13.1K Pulls 22 Tags Updated 1 week ago
The architecture is a partition, not a rebuild. All 64 layers keep the parent's attention side untouched: the 3 to 1 hybrid of gated deltanet layers and full attention, 16 attention layers in all, hidden size 5120. The surgery is in the feed forward. Each
147 Pulls 4 Tags Updated 1 week ago
Qwen3-TTS-12Hz-1.7B-Q4_K_M
158 Pulls 1 Tag Updated 1 week ago
Qwen3.8-27B Q4_K_M, default context 131072, tuned for a 32 GB NVIDIA RTX 5090.
54 Pulls 1 Tag Updated 1 week 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.
16.2K Pulls 3 Tags Updated 5 months ago
Infinitech Short description A powerful local AI assistant built on Qwen3 14B for reasoning, coding, problem-solving, and clear technical communication. Full description Infinitech is a thoughtful and capable local AI assistant powered by Qwen3 14B. It is
51 Pulls 1 Tag Updated 3 weeks ago
7,498 Pulls 1 Tag Updated 4 months ago
Qwen3.6-35B uncensored flagship: 1M certified 70/70, vision, MTP grafted. One file, four capabilities.
3,302 Pulls 2 Tags Updated 1 month 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.
7,735 Pulls 1 Tag Updated 5 months ago
Custom model for coding with agents to use locally with 16gb GPUs (working fine...)
1,897 Pulls 1 Tag Updated 2 months ago
Custom model for coding with agents to use locally with 16gb GPUs (working very fine...)
1,271 Pulls 1 Tag Updated 1 month ago
2,380 Pulls 1 Tag Updated 5 months ago
Custom model for coding with agents to use locally with 24gb GPUs - BEST FOR OPENCODE!
1,007 Pulls 1 Tag Updated 1 month ago
A coding-optimized configuration of Qwen3.5-9B designed for 16 GB single-GPU hardware. The model uses the official Q4_K_M quantization (~6.6 GB weights), leaving ~9 GB headroom for KV cache — enabling 32K+ context windows comfortably.
954 Pulls 1 Tag Updated 2 months ago
An attempt to compress Qwen3.5 into 500M and 1.5B parameters.
803 Pulls 2 Tags Updated 5 months ago