Peter's picture

11

Peter

rtzurtz

AI & ML interests

None yet

Organizations

None yet

New activity in Qwen/Qwen3-Next-80B-A3B-Instruct 2 months ago

How much Vram needed for the full context length?

#31 opened 5 months ago by

New activity in openai/gpt-oss-120b 3 months ago

Suggesting an open-weight Gpt-Oss LLM between the 20B and 120B parameters

#156 opened 3 months ago by

New activity in MiniMaxAI/MiniMax-M2 3 months ago

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

#20 opened 4 months ago by

New activity in unsloth/gpt-oss-20b-GGUF 3 months ago

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

#34 opened 4 months ago by

New activity in unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF 4 months ago

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

#8 opened 4 months ago by

New activity in unsloth/Qwen3-30B-A3B-GGUF 7 months ago

Any quants between Q8_K_XL and BF16?

#16 opened 7 months ago by

New activity in Qwen/Qwen3-235B-A22B-Instruct-2507 7 months ago

Good idea to remove the hybrid thinking mode

#16 opened 7 months ago by

New activity in bartowski/Qwen_Qwen3-30B-A3B-GGUF 7 months ago

A _Q8_K_XL quant?

#4 opened 7 months ago by

New activity in Qwen/Qwen3-32B 7 months ago

MoE version with the same performance as this 32B dense

#37 opened 7 months ago by

New activity in tencent/Hunyuan-A13B-Instruct 7 months ago

First evaluation suggest only 14B (dense) performance?

#33 opened 7 months ago by

New activity in Qwen/Qwen3-235B-A22B 8 months ago

Qwen is loosing broad knowledge since Qwen2.

#16 opened 10 months ago by