GPU Poor LLM Arena
🏆
297
Compact LLM Battle Arena: Frugal AI Face-Off!
Strix Halo 128G
Models to try on MAX+ 395 Strix Halo 128G GTT & Llama.cpp in ToolBox
-
mradermacher/gpt-oss-120b-heretic-v1-i1-GGUF
117B • Updated • 5.11kNote just for coding but fast
huihui-ai/Huihui-Qwen3-Next-80B-A3B-Instruct-abliterated
Text Generation • 81B • Updated • 812 • 11Note spectacular for fun authoring and fast
-
unsloth/GLM-4.6-REAP-268B-A32B-GGUF
Text Generation • 269B • Updated • 2.26k • 13 -
noctrex/INTELLECT-3-MXFP4_MOE-GGUF
Text Generation • 107B • Updated • 876 -
FBTMAML/KAT-Dev-72B-Exp
73B • Updated • 337 • 1 -
mradermacher/Qwen3-Coder-30B-A3B-IT-Heretic-i1-GGUF
31B • Updated • 3.98k • 3 -
noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF
Text Generation • 32B • Updated • 2.23k • 7 -
ggml-org/gpt-oss-120b-GGUF
117B • Updated • 381k • 50 -
yhavinga/GLM-4.7-REAP-40p-GGUF
218B • Updated • 1.72k • 2 -
jivank/GLM-4.7-REAP-40-GGUF
218B • Updated -
ggml-org/Devstral-Small-2-24B-Instruct-2512-GGUF
24B • Updated • 934 • 1