Mathieu Dugré

dugrema's activity

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

upvoted a collection 6 days ago

Gemma 4

Collection

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 25 items • Updated 2 days ago • 102

reactedto danielhanchen's post with 🔥 6 days ago

view post

Post

3530

Google releases Gemma 4. ✨
Gemma 4 introduces 4 models: E2B, E4B, 26B-A4B, 31B.
The multimodal reasoning models are under Apache 2.0.

Run E2B and E4B on ~6GB RAM, and on phones. Run 26B-A4B and 31B on ~18GB.

GGUFs: https://huggingface.co/collections/unsloth/gemma-4
Guide: https://unsloth.ai/docs/models/gemma-4

See translation

• 
• 
• 

🔥

22

22

🚀

8

8

👍

1

1

❤️

1

1

+

Reply

upvoted a collection 6 days ago

Gemma 4

Collection

8 items • Updated 6 days ago • 496

upvoted a collection 7 days ago

Granite Vision Models

Collection

Multimodal models built for visual document analysis and image understanding. • 6 items • Updated 7 days ago • 33

liked a model about 1 month ago

unsloth/Qwen3.5-27B-GGUF

Image-Text-to-Text • 27B • Updated Mar 5 • 719k • 452

New activity in unsloth/Qwen3.5-27B-GGUF about 1 month ago

Q3_K_XL?

👍 2

6

#2 opened about 1 month ago by

floory

liked 3 models about 1 month ago

unsloth/Qwen3.5-35B-A3B-GGUF

Image-Text-to-Text • 35B • Updated Mar 5 • 1.52M • 784

Qwen/Qwen3.5-35B-A3B

Image-Text-to-Text • 36B • Updated Feb 27 • 3.34M • • 1.34k

Qwen/Qwen3.5-27B

Image-Text-to-Text • 28B • Updated Feb 25 • 3.16M • • 890

New activity in Qwen/Qwen3.5-27B about 1 month ago

amazing model

❤️ 7

2

#5 opened about 1 month ago by

Tugay31

New activity in unsloth/Qwen3.5-35B-A3B-GGUF about 1 month ago

Coding parameters used for Goose and Zed

2

#3 opened about 1 month ago by

dugrema

upvoted 2 collections about 1 month ago

Qwen3.5

Collection

21 items • Updated about 1 month ago • 1.46k

Qwen3.5

Collection

Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B. • 25 items • Updated 4 days ago • 132

upvoted an article about 2 months ago

view article

Article

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

• 
• 
• +4

Feb 20

•

501

New activity in unsloth/MiniMax-M2.5-GGUF about 2 months ago

4-bit quantization: MXFP4_MOE vs Q4_K_XL?

4

#3 opened about 2 months ago by

fsaudm

New activity in unsloth/GLM-4.7-Flash-GGUF about 2 months ago

New uploads Feb 12th?

👍 1

2

#27 opened about 2 months ago by

jmagder

New activity in unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF 2 months ago

Performance is poor

13

#1 opened 2 months ago by

sainnhe

New activity in unsloth/GLM-4.7-Flash-GGUF 2 months ago

Jan 21: All GLM-4.7-Flash quants reuploaded - much better outputs!

🔥❤️ 7

29

#10 opened 3 months ago by

danielhanchen

DISABLE REPEAT PENALTY or set = 1.0

👍 6

7

#13 opened 2 months ago by

danielhanchen

liked a model 3 months ago

zai-org/GLM-4.7-Flash

Text Generation • 31B • Updated Jan 29 • 925k • • 1.66k