🤝 Open to Collab

Matt

Basher17

25 2 64

AI & ML interests

Uploading high-quality MLX quantizations of models I use.

Recent Activity

new activity 34 minutes ago

fastino/Fastino-Nemotron-3.5-Lightning-Finance:Is Bolt planned?

liked a model 35 minutes ago

fastino/Fastino-Nemotron-3.5-Lightning-Finance

new activity about 10 hours ago

wesjos/Qwen3.5-4B-Fuck:Fun, but how?

View all activity

Organizations

New activity in fastino/Fastino-Nemotron-3.5-Lightning-Finance 34 minutes ago

Is Bolt planned?

#8 opened 34 minutes ago by

Basher17

liked a model 35 minutes ago

fastino/Fastino-Nemotron-3.5-Lightning-Finance

Text Generation • 32B • Updated 7 days ago • 2.25k • 43

New activity in wesjos/Qwen3.5-4B-Fuck about 10 hours ago

Fun, but how?

#1 opened about 10 hours ago by

Basher17

liked a model about 10 hours ago

wesjos/Qwen3.5-4B-Fuck

Image-Text-to-Text • 5B • Updated 1 day ago • 115 • 2

liked a model about 11 hours ago

RecursiveSI/flint

Text Generation • 40B • Updated about 18 hours ago • 343

liked a model 2 days ago

domyn/Domyn-Edge-SFT

Text Generation • 4B • Updated about 17 hours ago • 63 • 2

New activity in Aleph-Alpha/Kolibri-1 2 days ago

Can someone produce a oQ4e quant?

#17 opened 3 days ago by

Basher17

reacted to gianlucamazza's post with 🔥 2 days ago

Post

3,305

GGUF models from xllama's catalogue, my independent research project for local LLM inference on an Xbox Series S. Each note gives the measured figures or test status, with model, quant and setup. For example, LFM2.5-350M (QAD Q4_0, Dev Mode, llama.cpp CPU) decodes at 101.6 tok/s. Source for every number: xllama's model matrix. Not affiliated with Microsoft.
gianlucamazza/xllama-models-measured-on-xbox-series-s-6aca0b32275cbe99dbf02d89