Johan Schmidt

johandevlabs's activity

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

reacted to BlueNipples's post with 👀 about 9 hours ago

view post

Post

1364

Good news, llama.cpp seems to be close to supporting MTP on qwen models. Bad news, every single gguf will have to be redone when it is.

See translation

• 
• 1 reply

·

👀

13

13

+

Reply

New activity in mistralai/Mistral-Medium-3.5-128B 2 days ago

Mistral 12B - 34B ?? Please 🥰

🔥 2

3

#8 opened 8 days ago by

UniversalLove333

liked a model 6 days ago

mistralai/Mistral-Medium-3.5-128B

128B • Updated 3 days ago • 18.3k • 293

liked a model 13 days ago

deepseek-ai/DeepSeek-V4-Flash

Text Generation • 158B • Updated 1 day ago • 751k • • 977

liked a model 21 days ago

unsloth/Qwen3.6-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated 17 days ago • 2.42M • 953

upvoted a collection 21 days ago

APEX Quants (GGUF)

Collection

MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) • 27 items • Updated 9 days ago • 87

New activity in mudler/gemma-4-26B-A4B-it-APEX-GGUF 23 days ago

new I-quants produce garbled output

4

#6 opened 23 days ago by

jdarthur

liked 2 models 27 days ago

mudler/Qwen3.5-35B-A3B-APEX-GGUF

Text Generation • 35B • Updated 10 days ago • 140k • 90

mudler/Qwen3.5-122B-A10B-APEX-GGUF

122B • Updated 10 days ago • 10.5k • 16