Steve Li's picture

Steve Li

CHNtentes

·

CHNtentes

AI & ML interests

None yet

Recent Activity

new activity about 8 hours ago

cpatonn/Qwen3-VL-8B-Instruct-AWQ-4bit:What framework was used to quantize Qwen3-VL? Is it llmcompressor?

upvoted a paper 7 days ago

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

new activity 10 days ago

Tongyi-MAI/Z-Image-Turbo:Thank You for your awesome Contribution to OS ✨

View all activity

Organizations

None yet

New activity in cpatonn/Qwen3-VL-8B-Instruct-AWQ-4bit about 8 hours ago

What framework was used to quantize Qwen3-VL? Is it llmcompressor?

#1 opened about 20 hours ago by

New activity in Tongyi-MAI/Z-Image-Turbo 10 days ago

Thank You for your awesome Contribution to OS ✨

#35 opened 10 days ago by

z-image models is specially only working with qwen3 4b ?

#24 opened 11 days ago by

New activity in Comfy-Org/z_image_turbo 11 days ago

fp8 plz? 🙏🏻

#3 opened 12 days ago by

New activity in T5B/Z-Image-Turbo-FP8 11 days ago

thanks!

#2 opened 11 days ago by

New activity in cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit 11 days ago

vLLM v0.11.1 seems to work, but v0.11.2 fails

#3 opened 13 days ago by

New activity in Tongyi-MAI/Z-Image-Turbo 12 days ago

What additional models of QWEN 3 4B we can use with Z Image?

#4 opened 12 days ago by

New activity in Qwen/Qwen3-4B-Instruct-2507 16 days ago

The model doesn't know about itself

#17 opened about 1 month ago by

New activity in cyankiwi/GLM-4.6-AWQ-4bit 19 days ago

Great quantized model

#1 opened 19 days ago by

New activity in cyankiwi/MiniMax-M2-AWQ-4bit 21 days ago

"observer": "mse" could improve accuracy?

#1 opened 21 days ago by

New activity in unsloth/Kimi-K2-Thinking-GGUF 26 days ago

Chat template fixes + FAQ

#2 opened about 1 month ago by

New activity in unsloth/MiniMax-M2-GGUF about 1 month ago

Pls MXFP4

#4 opened about 1 month ago by

New activity in MiniMaxAI/MiniMax-M2 about 1 month ago

mtp or other speculative decoding method?

#34 opened about 1 month ago by

New activity in unsloth/MiniMax-M2-GGUF about 1 month ago

first <think> token not getting outputted

#1 opened about 1 month ago by

New activity in Tongyi-MiA/UI-Ins-7B about 1 month ago

model weights are actually BF16, but config.json says FP32

#1 opened about 1 month ago by

New activity in moonshotai/Kimi-Linear-48B-A3B-Instruct about 1 month ago

Great size choice ! AWQ would be greatly appreciated.

#1 opened about 1 month ago by

New activity in Qwen/Qwen3-Omni-30B-A3B-Instruct about 1 month ago

When will the vLLM implementation with the Talker module be available?

#26 opened about 1 month ago by

mifanbushipeicai

New activity in MiniMaxAI/MiniMax-M2 about 1 month ago

Why does it keep trying to connect to huggingface?

#16 opened about 1 month ago by

New activity in inclusionAI/Ming-flash-omni-Preview about 1 month ago

vllm / sglang support?

#2 opened about 1 month ago by

New activity in cerebras/GLM-4.5-Air-REAP-82B-A12B about 1 month ago

Dual RTX Pro 6000 Blackwell 96GB - IT FITS!

#11 opened about 1 month ago by