medmekk/Qwen3.5-35B-A3B-MXFP4
21B • Updated • 3
Mohamed Mekkouri
medmekk
AI & ML interests
None yet
Recent Activity
updated a model about 1 month ago
medmekk/Qwen3.5-35B-A3B-MXFP4 published a model about 1 month ago
medmekk/Qwen3.5-35B-A3B-MXFP4 new activity 2 months ago
kernels-community/rmsnorm:Add Metal (Apple Silicon) build variantsOrganizations
medmekk/gpt-oss-120b-mxfp4
59B • Updated • 1
medmekk/gpt-oss-120b-mxfp4-hf
2B • Updated
medmekk/gpt-oss-20b-mxfp4-hf
2B • Updated • 1
medmekk/wc-gpt-oss-20b-mxfp4-conv
22B • Updated • 1
medmekk/Llama-3.2-1B-Instruct-metal
Text Generation • 0.4B • Updated • 990
medmekk/Llama-3.2-3B-Instruct-metal
Text Generation • 0.4B • Updated • 6
medmekk/sage-attention
Updated • 4
medmekk/bitsandbytes-mps
Updated
medmekk/Llama-3.2-1B-Instruct-bnb-nf4-double-quant
Text Generation • 1B • Updated • 6
medmekk/Llama-3.2-1B-Instruct-bnb-nf4
Text Generation • 1B • Updated • 2
medmekk/Llama-3.2-1B-Instruct-bnb
Text Generation • 1B • Updated • 5
medmekk/flash-mla
Updated
medmekk/deep-gemm
Updated
medmekk/Llama-3.2-3B-Instruct-mlx
Text Generation • 0.8B • Updated • 44
medmekk/test-mlx-quantized
Text Generation • 0.4B • Updated • 11
medmekk/quantization-mlx
Updated
medmekk/gpt-oss-20b
12B • Updated • 5
medmekk/MiniMax-M2-Small
Text Generation • 9B • Updated • 11
medmekk/Llama-3.2-Instruct-fpquant
1B • Updated • 1
medmekk/Llama-3.2-1B-Instruct-FP8-fbgemm-fp8
1B • Updated • 1
medmekk/gpt-oss-20b-mxfp4
2B • Updated • 3
medmekk/Llama-3.2-1B-float8-torchao-2
1B • Updated
medmekk/llama-3.2-1b-float8-torchao
1B • Updated • 1
medmekk/rmsnorm_kernel
Updated • 1
medmekk/llama-3.2-1b-hf
Text Generation • 1B • Updated • 5
medmekk/SmolLM3-3B-PTQ-Float8
Text Generation • Updated
medmekk/SmolLM3-3B-QAT-Float8
Text Generation • Updated • 1
medmekk/SmolLM3-3B-QAT-BF16
Text Generation • 3B • Updated • 2
medmekk/Meta-Llama-3.2-1B-torchao-aint8-wint8
Text Generation • Updated • 1