Mamy Ratsimbazafy
mratsim
AI & ML interests
Slop Hunter, Creative Sampler, Compressor of Weights, Bearer of the Quantizer Torch
Recent Activity
liked a dataset about 1 hour ago
nohurry/Opus-4.6-Reasoning-3000x-filtered new activity about 22 hours ago
mratsim/MiniMax-M2.5-BF16-INT4-AWQ:accuracy new activity about 24 hours ago
MiniMaxAI/MiniMax-M2.5:[Model bug] Typos issues with either quantization or Fp8 with transformers v5 (or both).Organizations
None yet
models 43
mratsim/MiniMax-M2.5-BF16-INT4-AWQ
Text Generation • 39B • Updated • 47.2k • 34
mratsim/MiniMax-M2.5-FP8-INT4-AWQ
Text Generation • 39B • Updated • 9.37k • 15
mratsim/GLM-4.7-Flash-FP8
Text Generation • 31B • Updated • 479 • 1
mratsim/MiniMax-M2.1-BF16-INT4-AWQ
Text Generation • 39B • Updated • 372 • 7
mratsim/MiniMax-M2.1-FP8-INT4-AWQ
Text Generation • Updated • 198 • 39
mratsim/GLM-4.7-EXL3
Text Generation • Updated • 39 • 19
mratsim/Hearthfire-24B-NVFP4A16
Text Generation • 14B • Updated • 2 • 1
mratsim/Codex-24B-Small-3.2-NVFP4A16
Text Generation • 14B • Updated • 2
mratsim/Hearthfire-24B-NVFP4
Text Generation • 14B • Updated • 17
mratsim/GLM-4.5-Iceblink-106B-A12B-FP8
Text Generation • 111B • Updated • 2 • 1
datasets 0
None public yet