Peter

rtzurtz's activity

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

New activity in Qwen/Qwen3.6-27B about 21 hours ago

Dense 60-120B

#44 opened about 21 hours ago by

rtzurtz

delete

#43 opened about 21 hours ago by

rtzurtz

New activity in unsloth/Qwen3.6-27B-MTP-GGUF 21 days ago

Report: 56 t/s on RTX 4090D (48GB VRAM) with UD-Q6_K_XL

3

#25 opened about 1 month ago by

SlavikF

New activity in Qwen/Qwen3.5-122B-A10B 3 months ago

40B to 80B dense LLM: A better/smarter model than 122B that can still fit

1

#16 opened 3 months ago by

rtzurtz

Thank you team Qwen for a 120B LLM

❤️ 3

2

#3 opened 4 months ago by

rtzurtz

New activity in unsloth/Qwen3.5-27B-GGUF 3 months ago

27B GGUF quants benchmark?

👀 1

1

#25 opened 3 months ago by

rtzurtz

when new updated version waiting

👀👍 3

1

#22 opened 3 months ago by

gopi87

New activity in Qwen/Qwen3.5-397B-A17B 4 months ago

Smaller GGUF without the vision weights?

1

#19 opened 4 months ago by

rtzurtz

New activity in Qwen/Qwen3-Next-80B-A3B-Instruct 7 months ago

How much Vram needed for the full context length?

6

#31 opened 9 months ago by

Aly87

New activity in openai/gpt-oss-120b 7 months ago

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

#156 opened 7 months ago by

rtzurtz

New activity in MiniMaxAI/MiniMax-M2 7 months ago

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

🤝👍 2

7

#20 opened 8 months ago by

rtzurtz

New activity in unsloth/gpt-oss-20b-GGUF 8 months ago

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

3

#34 opened 8 months ago by

rtzurtz

New activity in unsloth/Qwen3-235B-A22B-Instruct-2507-GGUF 9 months ago

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

5

#8 opened 9 months ago by

rtzurtz

New activity in unsloth/Qwen3-30B-A3B-GGUF 11 months ago

Any quants between Q8_K_XL and BF16?

1

#16 opened 11 months ago by

rtzurtz

New activity in Qwen/Qwen3-235B-A22B-Instruct-2507 11 months ago

Good idea to remove the hybrid thinking mode

👍 4

1

#16 opened 11 months ago by

rtzurtz

New activity in bartowski/Qwen_Qwen3-30B-A3B-GGUF 11 months ago

A _Q8_K_XL quant?

#4 opened 11 months ago by

rtzurtz

New activity in Qwen/Qwen3-32B 11 months ago

MoE version with the same performance as this 32B dense

#37 opened 11 months ago by

rtzurtz

New activity in tencent/Hunyuan-A13B-Instruct 12 months ago

First evaluation suggest only 14B (dense) performance?

👀 5

#33 opened 12 months ago by

rtzurtz

New activity in Qwen/Qwen3-235B-A22B 12 months ago

Qwen is loosing broad knowledge since Qwen2.

🔥👍 11

16

#16 opened about 1 year ago by

phil111