Mathieu Dugré's picture

Mathieu Dugré

dugrema

·

AI & ML interests

None yet

Recent Activity

new activity 5 days ago

unsloth/gemma-4-31B-it-GGUF:Do not use CUDA 13.2

upvoted a collection 11 days ago

reacted to danielhanchen's post with 🔥 11 days ago

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

View all activity

Organizations

None yet

upvoted 2 collections 11 days ago

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 28 items • Updated 2 days ago • 127

Gemma 4

8 items • Updated 12 days ago • 592

upvoted a collection 12 days ago

Granite Vision Models

Multimodal models built for visual document analysis and image understanding. • 6 items • Updated 13 days ago • 34

upvoted 2 collections about 2 months ago

Qwen3.5

21 items • Updated Mar 9 • 1.5k

Qwen3.5

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 10 days ago • 144

upvoted an article about 2 months ago

Article

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

+4

Feb 20

•

501

upvoted 6 collections 3 months ago

GLM-4.7

3 items • Updated Jan 19 • 65

TranslateGemma

3 items • Updated Mar 12 • 233

Whisper Release

Whisper includes both English-only and multilingual checkpoints for ASR and ST, ranging from 38M params for the tiny models to 1.5B params for large. • 12 items • Updated Sep 13, 2023 • 154

Qwen3-VL

37 items • Updated Dec 31, 2025 • 689

Unsloth Diffusion GGUFs

Find GGUFs and other variants of diffusion based models like Qwen-Image and FLUX. • 20 items • Updated 10 days ago • 74

Qwen3-VL

Qwen's new multimodal vision models in GGUF, safetensor, and dynamic Unsloth formats. • 56 items • Updated 10 days ago • 31

upvoted an article 5 months ago

Article

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

Nov 13, 2025

•

12

upvoted 7 collections 7 months ago

gpt-oss

OpenAI's gpt-oss-20b and gpt-oss-120b is here! The powerful open models are available in GGUF, original & 4-bit formats. • 16 items • Updated 10 days ago • 47

Gemma 3

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. • 54 items • Updated 10 days ago • 113

Qwen3

Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. • 70 items • Updated 10 days ago • 268

mmBERT: a modern multilingual encoder

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, 2025 • 53

gpt-oss

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7, 2025 • 429

Google's Gemma models family

334 items • Updated Mar 12 • 783

Unsloth Dynamic 2.0 Quants

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 85 items • Updated 2 days ago • 523