Mathieu Dugré's picture

2 16 5

Mathieu Dugré

dugrema

·

AI & ML interests

None yet

Recent Activity

upvoted a collection 3 days ago

upvoted a collection 3 days ago

Whisper Release

upvoted a collection 5 days ago

View all activity

Organizations

None yet

upvoted 2 collections 3 days ago

TranslateGemma

3 items • Updated 3 days ago • 138

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 • 148

upvoted a collection 5 days ago

Qwen3-VL

37 items • Updated 18 days ago • 581

liked a Space 6 days ago

Accurate GGUF VRAM Calculator

Calculate VRAM for GGUF models using GPU layers and context

upvoted a collection 9 days ago

Unsloth Diffusion GGUFs

Find GGUFs and other variants of diffusion based Qwen-Image and FLUX models. • 17 items • Updated 2 days ago • 25

upvoted a collection 12 days ago

Qwen3-VL

Qwen's new multimodal vision models in GGUF, safetensor, and dynamic Unsloth formats. • 56 items • Updated 25 days ago • 22

upvoted an article about 2 months ago

Article

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

Nov 13, 2025

•

7

New activity in openai/gpt-oss-20b 4 months ago

It seems to be censored a bit too much.

#62 opened 5 months ago by

New activity in unsloth/gpt-oss-20b-GGUF 4 months ago

Absurd sizes.

#12 opened 6 months ago by

upvoted 3 collections 4 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. • 18 items • Updated 25 days ago • 41

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. • 55 items • Updated 25 days ago • 103

Qwen3

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 25 days ago • 252

liked a model 4 months ago

jhu-clsp/mmBERT-base

Fill-Mask • Updated Oct 7, 2025 • 279k • • 178

upvoted 3 collections 4 months ago

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 • 50

gpt-oss

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7, 2025 • 405

Google's Gemma models family

335 items • Updated 3 days ago • 682

upvoted 2 collections 5 months ago

Unsloth Dynamic 2.0 Quants

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 67 items • Updated 18 days ago • 303

Gemma 3 QAT

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, 2025 • 215

liked a dataset 5 months ago

mit-han-lab/pile-val-backup

Viewer • Updated Aug 21, 2023 • 215k • 27.4k • 25

upvoted an article 5 months ago

Article

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

Aug 8, 2025

•

29