James Dumay

jamesdumay's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a dataset 5 days ago

olawaleibrahim/professionaldocuments

Viewer • Updated Jan 2, 2025 • 1.54k • 24 • 1

New activity in meshllm/qwen3.6-35b-a3b-gguf-moe 9 days ago

Publish Qwen3.6-35B-A3B-UD-Q4_K_XL full-v1 package (batch 1/11)

#4 opened 9 days ago by

jamesdumay

updated a model 9 days ago

meshllm/qwen3.6-35b-a3b-gguf-moe

Updated 10 days ago • 326

New activity in meshllm/qwen3.6-35b-a3b-gguf-moe 9 days ago

Publish Qwen3.6-35B-A3B-UD-Q4_K_XL full-v1 package (batch 1/30)

#3 opened 9 days ago by

jamesdumay

upvoted a paper 9 days ago

Accelerating MoE Model Inference with Expert Sharding

Paper • 2503.08467 • Published Mar 11, 2025 • 1

New activity in meshllm/qwen3.6-35b-a3b-gguf-moe 10 days ago

Publish Qwen3.6-35B-A3B-UD-Q4_K_XL full-v1 package (batch 1/34)

#2 opened 10 days ago by

jamesdumay

Publish Qwen3.6-35B-A3B-UD-Q4_K_XL full-v1 package (batch 1/34)

#1 opened 10 days ago by

jamesdumay

published a model 10 days ago

meshllm/qwen3.6-35b-a3b-gguf-moe

Updated 10 days ago • 326

updated a dataset 10 days ago

meshllm/catalog

Updated 10 days ago • 39

published a dataset 10 days ago

meshllm/catalog

Updated 10 days ago • 39

updated a dataset 11 days ago

meshllm/moe-rankings

Updated 11 days ago • 127 • 1

New activity in meshllm/moe-rankings 11 days ago

Add Qwen3.6-35B-A3B-UD-Q4_K_XL full-v1 expert components (batch 1/34)

#5 opened 11 days ago by

jamesdumay

Add Qwen3.6-35B-A3B-UD-Q4_K_XL full-v1 for unsloth/Qwen3.6-35B-A3B-GGUF@9280dd353ab5

#4 opened 11 days ago by

jamesdumay

New activity in meshllm/moe-rankings 16 days ago

Add google-gemma-4-26B-A4B-it-Q4_K_M full-v1 for batiai/Gemma-4-26B-A4B-it-GGUF@bedab587714a

#3 opened 16 days ago by

jamesdumay

updated 2 models 16 days ago

meshllm/qwen3-8b-parity-8bit-mlx

Text Generation • 8B • Updated 16 days ago • 51

meshllm/qwen3-8b-parity-q8_0-gguf

8B • Updated 16 days ago • 49 • 2

published 2 models 16 days ago

meshllm/qwen3-8b-parity-q8_0-gguf

8B • Updated 16 days ago • 49 • 2

meshllm/qwen3-8b-parity-8bit-mlx

Text Generation • 8B • Updated 16 days ago • 51

updated a model 18 days ago

meshllm/olmo-7b-instruct-hf-parity-bf16-mlx

Text Generation • 7B • Updated 18 days ago • 559

published a model 18 days ago

meshllm/olmo-7b-instruct-hf-parity-bf16-mlx

Text Generation • 7B • Updated 18 days ago • 559