Marcello Seri

mseri

·

https://mseri.me

AI & ML interests

None yet

Recent Activity

liked a model 8 days ago

ibm-granite/granite-speech-5.0-470m-turboctc

liked a model 8 days ago

ibm-granite/granite-speech-5.0-470m-turboctc-nc

updated a model 11 days ago

mseri/zunzuncito-maple-preview-2bit

View all activity

Organizations

upvoted a collection 16 days ago

Muse Glimmer

Muse Glimmer 30B: multimodal agentic model for local deployment. BF16 weights, GGUF k-quants, ExecuTorch builds, DFlash drafter. • 4 items • Updated 23 days ago • 106

upvoted a collection about 1 month 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 Jul 22 • 11

upvoted 2 collections about 2 months ago

Luciole LLM

Open Source LLM in French, English, German, Spanish, Italian, Portuguese, Dutch and Arabic • 14 items • Updated 5 days ago • 14

DFlash

Block Diffusion for Flash Speculative Decoding • 23 items • Updated Jun 28 • 156

upvoted an article 2 months ago

Article

Why Specialization Is Inevitable

Dharma-AI

•

Jun 30

• 18

upvoted a collection 2 months ago

Ornith-1.0

Ornith-1.0 is a family of open-source LLMs specialized for agentic coding. • 8 items • Updated 14 days ago • 391

upvoted 5 collections 3 months ago

PP-OCRv6

From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks • 20 items • Updated 19 days ago • 110

Mellum 2

Mellum2 model weights • 6 items • Updated Jun 1 • 128

Gemma 4 QAT

Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy. • 16 items • Updated 7 days ago • 120

Gemma 4 QAT Mobile

4 items • Updated Jul 21 • 51

Gemma 4 QAT Q4_0

19 items • Updated Jul 21 • 161

upvoted an article 4 months ago

Article

Granite 4.1 LLMs: How They’re Built

ibm-granite

•

Apr 29

• 91

upvoted a collection 4 months ago

DeepSeek-V4

9 items • Updated 2 days ago • 866

upvoted 5 collections 5 months ago

Ternary Bonsai

1.58-bit Bonsai models • 9 items • Updated Jun 4 • 107

Introspective Diffusion Language Models (I-DLM)

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

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 43 items • Updated 7 days ago • 259

Gemma 4

Our most intelligent open models to date • 16 items • Updated 13 days ago • 1.1k

Bonsai

1-bit Bonsai models • 7 items • Updated Jun 4 • 217

upvoted 2 collections 6 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. • 121 items • Updated 3 days ago • 818

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 7 days ago • 167