Mathieu Dugré

dugrema's activity

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

upvoted an article about 1 month ago

view article

Article

10 Best Open-Source LLM Models (2025 Updated): Llama 4, Qwen 3 and DeepSeek R1

• 

Nov 13

•

6

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

It seems to be censored a bit too much.

🤯 👍 10

7

#62 opened 5 months ago by

petwoe

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

Absurd sizes.

4

#12 opened 5 months ago by

ZeroWw

upvoted a collection 3 months ago

gpt-oss

Collection

OpenAI's gpt-oss-20b and gpt-oss-120b is here! The powerful open models are available in GGUF, original & 4-bit formats. • 18 items • Updated 7 days ago • 40

upvoted 2 collections 4 months ago

Gemma 3

Collection

All versions of Google's new multimodal models including QAT in 1B, 4B, 12B, and 27B sizes. In GGUF, dynamic 4-bit and 16-bit formats. • 55 items • Updated 7 days ago • 102

Qwen3

Collection

Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. • 79 items • Updated 7 days ago • 250

liked a model 4 months ago

jhu-clsp/mmBERT-base

Fill-Mask • Updated Oct 7 • 296k • • 172

upvoted 4 collections 4 months ago

mmBERT: a modern multilingual encoder

Collection

mmBERT is trained on 3T tokens from over 1800 languages, showing SoTA scores on benchmarks and exceptional low-resource performance • 16 items • Updated Sep 9 • 49

gpt-oss

Collection

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7 • 395

Google's Gemma models family

Collection

332 items • Updated 13 days ago • 645

Unsloth Dynamic 2.0 Quants

Collection

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 67 items • Updated about 10 hours ago • 289

upvoted a collection 5 months ago

Gemma 3 QAT

Collection

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated Jul 10 • 212

liked a dataset 5 months ago

mit-han-lab/pile-val-backup

Viewer • Updated Aug 21, 2023 • 215k • 25.8k • 25

upvoted an article 5 months ago

view article

Article

What’s MXFP4? The 4-Bit Secret Powering OpenAI’s GPT‑OSS Models on Modest Hardware

• 

Aug 8

•

29

reacted to AdinaY's post with 🔥 5 months ago

view post

Post

3563

Qwen3-30B-A3B-Thinking-2507 🔥 latest step in scaling thinking capabilities from Alibaba Qwen team.

Qwen/Qwen3-30B-A3B-Thinking-2507-FP8

✨ 30B total / 3B active - Apache 2.0
✨ Native 256K context
✨ SOTA coding, alignment, agentic reasoning

See translation

• 

🔥

9

9

+

Reply

liked a model 5 months ago

meta-llama/Meta-Llama-3-70B-Instruct

Text Generation • 71B • Updated Jun 18 • 56.9k • • 1.5k

upvoted a collection 5 months ago

Qwen3

Collection

84 items • Updated about 6 hours ago • 1.53k

liked a model 5 months ago

Qwen/Qwen3-Coder-480B-A35B-Instruct

Text Generation • 480B • Updated Aug 21 • 21.9k • • 1.26k