Article
15
Félix Marty
fxmarty
AI & ML interests
Neural network compression
Source separation
Recent Activity
updated a model 21 days ago
amd-quark/tiny-random-qwen3_moe_untie published a model 21 days ago
amd-quark/tiny-random-qwen3_moe_untie updated a model about 1 month ago
fxmarty/Qwen_Qwen3-30B-A3B-Instruct-2507-5-layersOrganizations
Articles 4
Article
4
AMD + 🤗: Large Language Models Out-of-the-Box Acceleration with AMD GPU
models 130
fxmarty/Qwen_Qwen3-30B-A3B-Instruct-2507-5-layers
Text Generation • Updated • 2
fxmarty/moonshotai_Kimi-K2-Instruct-0905-2-layers
Text Generation • Updated • 3
fxmarty/Llama-4-Scout-17B-16E-Instruct-2-layers-mxfp4
5B • Updated • 1.89k • 1
fxmarty/logs
Updated
fxmarty/qwen1.5_moe_a2.7b_chat_w_fp6_e3m2_a_fp6_e3m2
11B • Updated • 2.82k
fxmarty/qwen1.5_moe_a2.7b_chat_w_fp6_e2m3_a_fp6_e2m3
11B • Updated • 1
fxmarty/qwen1.5_moe_a2.7b_chat_w_fp4_a_fp6_e2m3
8B • Updated • 2.63k
fxmarty/Llama-3.1-70B-Instruct-2-layers-mxfp6
3B • Updated • 2k
fxmarty/Mixtral-8x7B-Instruct-v0.1-FP8-KV-2-layers
3B • Updated • 5
fxmarty/Mixtral-8x7B-Instruct-v0.1-2-layers
3B • Updated