x-polyglot-x

x-polyglot-x's activity

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

New activity in ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF 10 days ago

Strata cannot load the model

5

#19 opened 14 days ago by

x-polyglot-x

New activity in antirez/deepseek-v4.1-flash-gguf 14 days ago

Plans for DS4.1-0107?

#11 opened 14 days ago by

x-polyglot-x

New activity in moonshotai/Kimi-K3 16 days ago

Kimi K3 (2.78T) running on a 128 GB MacBook Pro at ~1 tok/s, experts streamed from four SSDs

👍 1

5

#185 opened about 2 months ago by

konstantinnikol

New activity in antirez/kimi-k3-gguf about 1 month ago

kimi-k3.vision = false and no mmproj

👍 1

1

#1 opened 3 months ago by

erichartford

New activity in antirez/glm-5.3-gguf about 1 month ago

Inference speeds compared to DS4.1 Flash?

1

#2 opened about 1 month ago by

x-polyglot-x

New activity in Justvugg/GLM-5.3-Flash-colibri-int4-g64 2 months ago

Thank you!

2

#1 opened 2 months ago by

x-polyglot-x

New activity in moonshotai/Kimi-K3 3 months ago

I researched the practical GPU specs for Kimi-K3 — a few findings that surprised me more...

🔥 1

1

#171 opened 3 months ago by

hexgridcloud

New activity in unsloth/Qwen3.8-27B-GGUF 3 months ago

Qwen3.8-27B only 18 tok/s vs Qwen3.6-27B 62 tok/s on A100 80GB + vLLM — expected?

👍 4

5

#66 opened 3 months ago by

Alecone

New activity in Kwaipilot/KAT-Coder-V2.5-Dev 3 months ago

Still Waiting for Vision 👀 > Stopped Waiting. Transplanted One.

👍❤️ 6

7

#14 opened 3 months ago by

KennyVo

New activity in moonshotai/Kimi-K3 3 months ago

This might be the cheapest GPU type for Kimi K3 with 100% Data-on-GPU — Gift for AMD MI300x8

😎 2

11

#168 opened 3 months ago by

ghostplant

Waste engine: Run the full 2.78T-parameter Kimi K3 on a laptop

🔥 23

26

#148 opened 3 months ago by

marcobambini

New activity in unsloth/Kimi-K3-GGUF 3 months ago

Can i run this on my macbook?

👀🤯 4

5

#5 opened 3 months ago by

hugginface536

New activity in unsloth/MiniMax-M3-GGUF 5 months ago

tested UD-Q4_K_XL - it is terrible vs DS4F

5

#9 opened 5 months ago by

alexbi29

New activity in unsloth/Kimi-K2.7-Code-GGUF 5 months ago

Q8_K_XL seems small

1

#10 opened 5 months ago by

etemiz

New activity in moonshotai/Kimi-K2.7-Code 5 months ago

Consumer sized versions? (26B A3B Versions)

👍🔥 9

5

#5 opened 5 months ago by

CYISNOTHERE

MLX g32 bf16 conversion for TP=2 Mac Studios @20.1 tok/s average

👍 4

5

#7 opened 5 months ago by

whistlercapital

New activity in unsloth/Kimi-K2.7-Code-GGUF 5 months ago

Excited for this one!

👍 3

#3 opened 5 months ago by

x-polyglot-x

New activity in unsloth/Step-3.7-Flash-GGUF 5 months ago

How does this model fare?

9

#4 opened 5 months ago by

x-polyglot-x

New activity in unsloth/DeepSeek-V4-Flash 6 months ago

Worse than (smaller) MiniMax M2.7??

17

#2 opened 7 months ago by deleted

New activity in mlx-community/Kimi-K2.6-MoE-Smart-Quant 6 months ago

Is the model conversion done?

👍👀 3

2

#1 opened 6 months ago by

Seth-TW