Hybrid q4/q8 ROCmFPX GGUF quants. Requires the ROCmFPX fork of llama.cpp.
Jack PRO
JackBinary
AI & ML interests
None yet
Recent Activity
liked a model 3 days ago
zerofata/G4-MeroMero-26B-A4B updated a collection 3 days ago
ROCmFPX GGUF Quants updated a model 3 days ago
JackBinary/ROCmFPX-Quantize-PlaybookOrganizations
None yet
Experimental models with weird architectures. Frankenmerges, layer duplications, expert pruning, expert merging, and whatever else seems worth trying.
-
JackBinary/Qwen3.5-24B-A3B-Claude-Opus-Gemini-3.1-Pro-Reasoning-Distilled-heretic
Text Generation • 24B • Updated • 15 -
JackBinary/Qwen3.5-24B-A3B-Claude-Opus-Gemini-3.1-Pro-Reasoning-Distilled
Text Generation • 24B • Updated • 15 -
JackBinary/Qwen-3.5-10B-Frankenmerge-Opus-4.6-Distill
10B • Updated • 11 -
JackBinary/Qwen-3.5-10B-Frankenmerge-Opus-4.6-Distill-GGUF
10B • Updated • 53 • 1
Hybrid q4/q8 ROCmFPX GGUF quants. Requires the ROCmFPX fork of llama.cpp.
Experimental models with weird architectures. Frankenmerges, layer duplications, expert pruning, expert merging, and whatever else seems worth trying.
-
JackBinary/Qwen3.5-24B-A3B-Claude-Opus-Gemini-3.1-Pro-Reasoning-Distilled-heretic
Text Generation • 24B • Updated • 15 -
JackBinary/Qwen3.5-24B-A3B-Claude-Opus-Gemini-3.1-Pro-Reasoning-Distilled
Text Generation • 24B • Updated • 15 -
JackBinary/Qwen-3.5-10B-Frankenmerge-Opus-4.6-Distill
10B • Updated • 11 -
JackBinary/Qwen-3.5-10B-Frankenmerge-Opus-4.6-Distill-GGUF
10B • Updated • 53 • 1
OpenCodeReasoning-Nemotron-1.1 models (7B, 14B, 32B) in MLC format at various quants.