Zhukov

Geximus's activity

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

upvoted an article 4 days ago

view article

Article

Speculative Decoding in Practice: How EAGLE3 Makes LLMs Faster Without Changing Their Outputs

• 

24 days ago

•

8

New activity in demon-zombie/MiniMax-M2.7-AWQ-4bit 11 days ago

These are NOT actual AWQ-quantized models.

2

#1 opened 11 days ago by

cai-cai

New activity in MiniMaxAI/MiniMax-M2.7 12 days ago

MiniMax-M2.7 is highly verbose and slow

2

#18 opened 12 days ago by

weisunding

New activity in cyankiwi/MiniMax-M2.7-AWQ-4bit 12 days ago

thanks for 4bit awq!

🔥 3

1

#1 opened 13 days ago by

morlz

upvoted an article 13 days ago

view article

Article

2x Faster on a 229B MoE: EAGLE3 Speculative Decoding for MiniMax-M2.5

• 

17 days ago

•

3

liked a model 13 days ago

cyankiwi/MiniMax-M2.7-AWQ-4bit

Text Generation • 37B • Updated 13 days ago • 138k • 27

New activity in cyankiwi/MiniMax-M2.5-AWQ-4bit 14 days ago

Is minimax 2.7 on the way?

👍 1

1

#3 opened 14 days ago by

Geximus

New activity in MiniMaxAI/MiniMax-M2.5 16 days ago

Minimax 2.7???

49

#53 opened about 1 month ago by

rombodawg

New activity in togethercomputer/Aurora-Spec-Minimax-M2.5 24 days ago

Perfomance question

2

#4 opened 24 days ago by

Geximus

liked a model about 2 months ago

cyankiwi/Qwen3.5-122B-A10B-AWQ-8bit

Image-Text-to-Text • 39B • Updated Mar 26 • 3.29k • 3

liked a model 3 months ago

cyankiwi/Qwen3-Coder-Next-AWQ-4bit

Text Generation • 14B • Updated Mar 26 • 117k • 28

New activity in Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice 3 months ago

Low generation speed and low GPU utilization (~12%) during inference

😔👀 2

7

#18 opened 3 months ago by

Geximus

liked 2 models 3 months ago

cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit

Text Generation • 5B • Updated Mar 23 • 36.5k • 31

ai-sage/GigaAM-v3

Automatic Speech Recognition • Updated Nov 19, 2025 • 106k • 96

New activity in black-forest-labs/FLUX.2-dev 4 months ago

Why is Flux 2 so slow in Img2Img even though everything is in CUDA?

3

#22 opened 5 months ago by

Fredtt3

New activity in cyankiwi/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit 4 months ago

Perfomance of this model is one of the best

🤗👍 2

2

#13 opened 4 months ago by

Geximus

liked a Space 5 months ago

Running

Agents

64

Qwen TTS Clone Demo

👀

64

Create a custom voice clone and synthesize speech

New activity in cyankiwi/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit 5 months ago

why recently re-uploaded the core?

2

#7 opened 5 months ago by

Geximus

liked a model 5 months ago

cyankiwi/Qwen3-Next-80B-A3B-Thinking-AWQ-8bit

Text Generation • 25B • Updated Feb 3 • 36 • 5

upvoted a collection 7 months ago

Qwen3Guard

Collection

7 items • Updated Dec 31, 2025 • 66