ken

madc's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection about 13 hours ago

GMCE: GMCoder Efficiency models

Collection

Same models, far fewer tokens. GMCoder-style efficiency fine-tunes of Qwen3.5, Nanbeige and K2-Horizon. • 8 items • Updated about 9 hours ago • 1

upvoted a collection about 14 hours ago

Spark-X2.6

Collection

SOTA On-Device LLMs. Advancing the Frontier of On-Device Agents for Real-World Tasks. • 6 items • Updated about 17 hours ago • 14

upvoted 2 collections 1 day ago

Qwen 3.6 - Reg/Uncensored 9b, 12b, 21b, 27b, 40B

Collection

Fine tuned Qwen 3.6/3.8 models, including source and GGUF from 9B and up. 9B,12B, 21B and 40B are custom built by me. Tuning : Unsloth / COLD FUSION. • 31 items • Updated about 1 hour ago • 86

APEX Quants (GGUF)

Collection

MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) • 49 items • Updated 8 days ago • 153

upvoted a collection 2 days ago

MiroThinker-1.7

Collection

2 items • Updated Apr 25 • 4

upvoted a collection 3 days ago

APEX-I MiniPlus V2.1 — Standard (MoE)

Collection

Official APEX-I MiniPlus V2.1 (aprox. 14 GB) standard base and aligned Mixture-of-Experts and linear convnet architectures. • 15 items • Updated 7 days ago • 2

upvoted 3 collections 4 days ago

Mellum 2

Collection

Mellum2 model weights • 6 items • Updated Jun 1 • 137

Mellum2 GGUF

Collection

Mellum2 GGUF weights • 10 items • Updated Jun 4 • 18

Qwen3.8-3.6-27B Blend

Collection

Junie Local's unofficial JetBrains 50/50 blend of Qwen3.6-27B and Qwen3.8-27B: BF16, GGUF, and MLX weights. • 5 items • Updated 23 days ago • 10

upvoted 2 collections 5 days ago

K2 Horizon GGUF

Collection

5 items • Updated 7 days ago • 3

Jais 3 GGUF

Collection

GGUF versions of Jais 3 for llama.cpp • 5 items • Updated 7 days ago • 1