Ttimms/KAT-Coder-V2.5-Dev-REAP-50-bf16
Text Generation • 19B • Updated • 861
🕊️ God is the source code.
Tremayne Timms
Ttimms
AI & ML interests
Making big open models fit on one 16 GB consumer GPU. NVFP4 (Blackwell-native), GGUF, and REAP expert-pruned MoEs — every release ships with measured evals.
Recent Activity
updated a model about 15 hours ago
Ttimms/KAT-Coder-V2.5-Dev-REAP-50-bf16 updated a model about 15 hours ago
Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF updated a model about 15 hours ago
Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16-GPTQOrganizations
None yet
updated 7
models about 15 hours ago
Ttimms/KAT-Coder-V2.5-Dev-REAP-50-GGUF
Text Generation • 19B • Updated • 1.01k • 2
Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16-GPTQ
Text Generation • 19B • Updated • 58
Ttimms/Ornith-1.5-35B-A3B-REAP-50-bf16
Text Generation • 19B • Updated • 1.02k
Ttimms/Ornith-1.5-35B-A3B-REAP-50-GGUF
Text Generation • 19B • Updated • 1.09k • 2
Ttimms/Ornith-1.5-35B-A3B-REAP-50-NVFP4A16
Text Generation • 19B • Updated • 1.07k • 3
Ttimms/KAT-Coder-V2.5-Dev-REAP-50-NVFP4A16
Text Generation • 19B • Updated • 1.8k
updated a
model about 16 hours ago
upvoted 5
papers about 18 hours ago
Compressed Convolutional Attention: Efficient Attention in a Compressed Latent Space
Paper • 2510.04476 • Published • 16
Training Foundation Models on a Full-Stack AMD Platform: Compute, Networking, and System Design
Paper • 2511.17127 • Published • 4
The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility
Paper • 2605.19537 • Published • 2
REAP the Experts: Why Pruning Prevails for One-Shot MoE compression
Paper • 2510.13999 • Published • 23
KAT-Coder-V2.5 Technical Report
Paper • 2607.05471 • Published • 13
liked 7
models about 18 hours ago
Qwen/Qwen3.5-4B-Base
Image-Text-to-Text • 5B • Updated • 489k • 86
Zyphra/ZAYA1-base
Text Generation • 9B • Updated • 185 • 45
ornith-ai/Ornith-1.5-35B-A3B
Text Generation • 36B • Updated • 268k • 549
Kwaipilot/KAT-Coder-V2.5-Dev
Text Generation • 35B • Updated • 45.1k • 628
zai-org/GLM-5.3-Flash
Image-Text-to-Text • 321B • Updated • 728k • • 2.08k
zai-org/GLM-5.3
Text Generation • 753B • Updated • 370k • • 1.72k
Qwen/Qwen3.8-Flash-Next
Image-Text-to-Text • 180B • Updated • 401k • 4.92k