ken

madc's activity

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

upvoted 2 collections 1 day ago

MiniCPM-OCR

Collection

Fast, accurate OCR with correctness assessment. • 10 items • Updated about 3 hours ago • 15

💧 LFM3

Collection

Collection of base and post-trained LFM3 models (www.liquid.ai/blog/lfm3). • 7 items • Updated about 8 hours ago • 172

upvoted 4 collections 2 days ago

⚗️ Knowledge Distillation

Collection

Distilled models and datasets by xtools-at • 11 items • Updated about 8 hours ago • 2

⚔️ Qwensploit / Cybersec

Collection

Awesome fine-tunes for cyber security, vulnerability research, blue- and red teaming • 7 items • Updated 1 day ago • 3

👾9️⃣ Awesome Qwen3.5-9B

Collection

Awesome Qwen3.5-9B fine-tunes (~5.7GB @ Q4_K_M / ~9.5GB @ Q8_0 / ~18GB @ F16) • 23 items • Updated 1 day ago • 2

🥐 Awesome Mistral

Collection

Awesome Mistral fine-tunes • 9 items • Updated 1 day ago • 2

upvoted 6 collections 3 days ago

GSQ-RCO-GGUF

Collection

GGUF quantizations via GSQ + RCO: per-tensor mixed precision in standard GGUF form • 6 items • Updated 1 day ago • 4

DARWIN-Family

Collection

비드래프트 • 57 items • Updated 1 day ago • 33

Armoring Models

Collection

4 items • Updated Sep 28 • 17

POCKET-MODELs

Collection

13 items • Updated 27 days ago • 26

IQuest-Coder

Collection

14 items • Updated Mar 3 • 115

IQuest-Coder-V1-14B-Thinking

Collection

Quantized versions of IQuest-Coder-V1-14B-Thinking (GGUF, FP8, INT4, INT8,mlx-8bit). • 5 items • Updated Mar 27 • 1

upvoted 4 collections 4 days ago

System-Two

Collection

12 items • Updated 2 days ago • 19

GSQ-RCO-GGUF

Collection

Non-uniform GGUF quantizations via GSQ + RCO: per-tensor mixed precision in standard GGUF form • 4 items • Updated 4 days ago • 85

Agens Volundr 32B v1

Collection

Agens Volundr 32B v1 (2026-10-18): bf16, INT4, GGUF, DFlash2 drafter and the Engine-16GB build. • 6 items • Updated 10 days ago • 3

Esper 4

Collection

Esper 4 is an agentic finetune focused on code, DevOps, architecture, and MLOps! Currently available for Qwen 3.6 and Gemma 4. • 3 items • Updated Aug 13 • 4

upvoted a collection 5 days ago

APEX-I NanoPlus — Abliterated (MoE)

Collection

Official APEX-I NanoPlus (aprox. 11 to 12 GB) uncensored and abliterated Mixture-of-Experts architectures for 16 GB GPUs. • 3 items • Updated 3 days ago • 1

upvoted 3 collections 6 days ago

⚡️Qwopus3.8

Collection

4 items • Updated Sep 21 • 12

💻 Qwopus-Coder

Collection

Reasoning-distilled coding models optimized for specialized domains like agentic workflows. • 12 items • Updated 16 days ago • 59

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. • 17 items • Updated 3 days ago • 3