Edit Models filters

Apps

Docker Model Runner

Inference Providers

HF Inference API

Misc

Inference Endpoints

text-generation-inference

4-bit precision

8-bit precision

text-embeddings-inference

Carbon Emissions

Mixture of Experts

Models

1,190

Full-text search

Active filters: qwen3_moe

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_gate_ckpt285

31B • Updated Jun 12 • 4

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_gate_ckpt57

31B • Updated Jun 12 • 4

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_gate_ckpt114

31B • Updated Jun 12 • 4

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_gate_ckpt171

31B • Updated Jun 12 • 4

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_gate_ckpt228

31B • Updated Jun 12 • 4

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_gate_fixed_ckpt285

31B • Updated Jun 12 • 4

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_gate_fixed_ckpt57

31B • Updated Jun 12 • 3

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_gate_fixed_ckpt114

31B • Updated Jun 12 • 4

huihui-ai/Huihui-MoE-1B-A0.6B-SFT

Text Generation • 1B • Updated Jun 13 • 21

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_gate_fixed_ckpt171

31B • Updated Jun 12 • 4

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_gate_fixed_ckpt228

31B • Updated Jun 12 • 4

Jellon/Qwen3-30B-A3B-exl2-6bpw

Text Generation • Updated Jun 13 • 7

Jellon/Qwen3-30B-A3B-exl2-4bpw

Text Generation • Updated Jun 13 • 14

fengyao1909/ste_nemocode_sl16k_bs64_ptscle_fxep_lr3e-5_ckpt553

31B • Updated Jun 13 • 4

fengyao1909/ste_nemocode_sl16k_bs64_ptscle_fxep_lr5e-5_ckpt553

31B • Updated Jun 13 • 4

fengyao1909/ste_nemocode_sl16k_bs64_ptscle_fxep_lr3e-5_ckpt100

31B • Updated Jun 13 • 4

fengyao1909/ste_nemocode_sl16k_bs64_ptscle_fxep_lr5e-5_ckpt100

31B • Updated Jun 13 • 4

fengyao1909/ste_nemocode_sl16k_bs64_ptscle_fxep_lr3e-5_ckpt200

31B • Updated Jun 13 • 4

fengyao1909/ste_nemocode_sl16k_bs64_ptscle_fxep_lr5e-5_ckpt200

31B • Updated Jun 13 • 4

fengyao1909/ste_nemocode_sl16k_bs64_ptscle_fxep_lr3e-5_ckpt300

31B • Updated Jun 13 • 4

fengyao1909/ste_nemocode_sl16k_bs64_ptscle_fxep_lr5e-5_ckpt300

31B • Updated Jun 13 • 4

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_partscale_fixed_ex_normdtch_ckpt285

31B • Updated Jun 13 • 5

fengyao1909/ste_nemocode_sl16k_bs64_ptscle_fxep_lr3e-5_ckpt400

31B • Updated Jun 13 • 4

fengyao1909/ste_nemocode_sl16k_bs64_ptscle_fxep_lr5e-5_ckpt400

31B • Updated Jun 13 • 4

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_partscale_fixed_ex_normdtch_ckpt57

31B • Updated Jun 13 • 4

fengyao1909/ste_nemocode_sl16k_bs64_ptscle_fxep_lr3e-5_ckpt500

31B • Updated Jun 13 • 4

fengyao1909/ste_nemocode_sl16k_bs64_ptscle_fxep_lr5e-5_ckpt500

31B • Updated Jun 13 • 4

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_partscale_fixed_ex_normdtch_ckpt114

31B • Updated Jun 13 • 4

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_partscale_fixed_ex_normdtch_ckpt171

31B • Updated Jun 13 • 4

fengyao1909/ste_s1_sl16k_bs16_lr1e-5_zero3_partscale_fixed_ex_normdtch_ckpt228

31B • Updated Jun 13 • 4