Peter

rtzurtz's activity

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

New activity in MiniMaxAI/MiniMax-M2 7 days ago

230B vs 235B: Why no comparison against Qwen3-235B-A22B-Thinking-2507 ?

🤝 👍 2

2

#20 opened 7 days ago by

rtzurtz

New activity in unsloth/gpt-oss-20b-GGUF 16 days ago

Are the F16 weights upcasted MXFP4? -- Why no `gpt-oss-20b-MXFP4.gguf`?

2

#34 opened 16 days ago by

rtzurtz

New activity in unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF about 1 month ago

Q3_K_M (112 GB) is bigger than Q3_K_XL (104 GB)?

1

#8 opened about 1 month ago by

rtzurtz

New activity in unsloth/Qwen3-30B-A3B-GGUF 3 months ago

Any quants between Q8_K_XL and BF16?

1

#16 opened 3 months ago by

rtzurtz

New activity in Qwen/Qwen3-235B-A22B-Instruct-2507 3 months ago

Good idea to remove the hybrid thinking mode

👍 4

1

#16 opened 3 months ago by

rtzurtz

New activity in bartowski/Qwen_Qwen3-30B-A3B-GGUF 4 months ago

A _Q8_K_XL quant?

#4 opened 4 months ago by

rtzurtz

New activity in Qwen/Qwen3-32B 4 months ago

MoE version with the same performance as this 32B dense

#37 opened 4 months ago by

rtzurtz

New activity in tencent/Hunyuan-A13B-Instruct 4 months ago

First evaluation suggest only 14B (dense) performance?

👀 4

#33 opened 4 months ago by

rtzurtz

New activity in Qwen/Qwen3-235B-A22B 4 months ago

Qwen is loosing broad knowledge since Qwen2.

🔥 👍 12

16

#16 opened 6 months ago by

phil111