Marcello Seri

mseri

·

https://mseri.me

AI & ML interests

None yet

Recent Activity

liked a model about 10 hours ago

moonshotai/Kimi-K3

liked a model 2 days ago

owensong/Inflect-Micro-v2

liked a model 4 days ago

swiss-ai/Apertus-v1.5-8B

View all activity

Organizations

upvoted a collection 5 days ago

Cactus Hybrid

A small, on-device model is fast and private, but sometimes wrong. We post-train models to know when they are wrong, run on any framework. • 4 items • Updated 6 days ago • 7

upvoted a collection 11 days ago

Luciole LLM

Open Source LLM in French, English, German, Spanish, Italian, Portuguese, Dutch and Arabic • 14 items • Updated 19 days ago • 14

upvoted a collection 18 days ago

DFlash

Block Diffusion for Flash Speculative Decoding • 23 items • Updated 30 days ago • 151

upvoted an article 26 days ago

Article

Why Specialization Is Inevitable

Dharma-AI

•

28 days ago

• 17

upvoted 2 collections about 1 month ago

Ornith-1.0

Ornith-1.0 is a family of open-source LLMs specialized for agentic coding. • 8 items • Updated Jun 27 • 358

PP-OCRv6

From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks • 19 items • Updated Jun 15 • 106

upvoted 4 collections about 2 months ago

Mellum 2

Mellum2 model weights • 6 items • Updated Jun 1 • 126

Gemma 4 QAT

Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy. • 16 items • Updated 10 days ago • 112

Gemma 4 QAT Mobile

4 items • Updated 6 days ago • 48

Gemma 4 QAT Q4_0

19 items • Updated 6 days ago • 149

upvoted an article 3 months ago

Article

Granite 4.1 LLMs: How They’re Built

ibm-granite

•

Apr 29

• 85

upvoted 3 collections 3 months ago

DeepSeek-V4

6 items • Updated Jun 27 • 756

Ternary Bonsai

1.58-bit Bonsai models • 9 items • Updated Jun 4 • 101

Introspective Diffusion Language Models (I-DLM)

Model checkpoints for I-DLM. Paper: https://arxiv.org/abs/2604.11035 • 3 items • Updated Apr 14 • 11

upvoted 3 collections 4 months ago

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 43 items • Updated 10 days ago • 250

Gemma 4

16 items • Updated 6 days ago • 1.05k

Bonsai

1-bit Bonsai models • 7 items • Updated Jun 4 • 214

upvoted 3 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. • 110 items • Updated 1 day ago • 774

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 • 164

Parakeet ASR

NeMo Parakeet ASR Models attain strong speech recognition accuracy while being efficient for inference. Available in CTC and RNN-Transducer variants. • 16 items • Updated 11 days ago • 80