Tom Pfeil

Tompai's activity

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

liked a model 18 days ago

ubergarm/Qwen3.5-397B-A17B-GGUF

Text Generation • 396B • Updated 12 days ago • 15.4k • 30

New activity in unsloth/Qwen3.5-122B-A10B-GGUF 18 days ago

KLD/PPL of quants

❤️ 👍 9

1

#8 opened 19 days ago by

krampenschiesser

liked a model 19 days ago

lmstudio-community/Qwen3.5-35B-A3B-GGUF

35B • Updated 21 days ago • 434k • 16

liked a model 29 days ago

AesSedai/MiniMax-M2.5-GGUF

229B • Updated 30 days ago • 3.68k • 26

liked a model about 1 month ago

MiniMaxAI/MiniMax-M2.5

Text Generation • 229B • Updated 7 days ago • 540k • • 1.22k

liked a model 3 months ago

unsloth/MiniMax-M2.1-GGUF

Text Generation • 229B • Updated Feb 14 • 9.86k • 194

New activity in unsloth/MiniMax-M2.1-GGUF 3 months ago

Does it make sense to have UD-IQ4_XS?

2

#4 opened 3 months ago by

tarruda

liked 2 models 3 months ago

unsloth/GLM-4.7-GGUF

Text Generation • 358B • Updated Dec 27, 2025 • 10.3k • 213

MiniMaxAI/MiniMax-M2.1

Text Generation • 229B • Updated Feb 13 • 52.4k • • 1.27k

liked a model 4 months ago

Downtown-Case/GLM-4.6-128GB-RAM-IK-GGUF

Text Generation • 357B • Updated Dec 19, 2025 • 135 • 19

New activity in catalystsec/MiniMax-M2-4bit-DWQ 5 months ago

3-bit DWQ Version

#1 opened 5 months ago by

Tompai

upvoted a collection 6 months ago

Qwen3-Next

Collection

4 items • Updated Dec 31, 2025 • 186

New activity in mrtoots/unsloth-GLM-4.5-MLX-2Bit 7 months ago

Awful loss of coherence between MLX 2bit and IQ2_XSS 🙀

7

#2 opened 7 months ago by

overhead520

liked a dataset 7 months ago

HuggingFaceH4/Multilingual-Thinking

Viewer • Updated Aug 7, 2025 • 1k • 14.5k • 112

liked a model 7 months ago

mlx-community/Qwen3-235B-A22B-Thinking-2507-3bit-DWQ

Text Generation • Updated Jul 26, 2025 • 77 • 6

New activity in mlx-community/GLM-4.5-4bit 7 months ago

Is a 2-bit (DWQ) version possible?

#2 opened 7 months ago by

Tompai

liked a model 8 months ago

Qwen/Qwen3-Coder-30B-A3B-Instruct

Text Generation • Updated Dec 3, 2025 • 1.04M • • 978

New activity in mlx-community/Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr8e-8 8 months ago

What does the abbreviation “lr8e-8” stand for?

#1 opened 8 months ago by

Tompai

New activity in mlx-community/Llama-3_3-Nemotron-Super-49B-v1-mlx-4bit 10 months ago

[LM Studio]Error in iterating prediction stream: AttributeError: 'NoneType' object has no attribute 'shape'. Error Data: n/a, Additional Data: n/a

5

#2 opened 10 months ago by

izerwu

New activity in mlx-community/Qwen3-30B-A3B-mixed-3-4bit 11 months ago

What is the difference to mlx-community/Qwen3-30B-A3B-4bit ?

➕ 1

2

#1 opened 11 months ago by

Tompai