Hugging Face's logo
MadMike's picture
🦥 unsloth my mind

MadMike

MadMike477
23 127
BlueBroTech's profile picture thomaslinda68907's profile picture RexTRO111's profile picture
·

AI & ML interests

Love helping people <3, love tech, always learning <3 AI/ML enthusiast, training & fine-tuning models 🦥 Local LLMs & Unsloth <3

Recent Activity

liked a Space about 4 hours ago
suvadityamuk/3d-representations-guide
liked a Space about 21 hours ago
HuggingEnvs/geoguesser-article
reacted to OppaAI's post with 🔥 1 day ago
Another small 4B model comes out yesterday. NeoHorse 1 4B https://huggingface.co/TokenRhythm/NeoHorse-1-4B There are quite a few good smaller parameter models that are capable for Agentic tasks: The ones from the chart, I have tried a few already in my Jetson Orin Nano, ❌Gemma4 E2B IT - cannot fit my RAM usage if use with TTS and embedder ❓Qwen3.5 4B - just barely fit my RAM usage, need to add think/no_think ❌Spark X2.5 4B - need to build the forked llama.cpp; no vision ➡️Nanbeige 4.2 3B - need to build the forked llama.cpp; slower than Ministral3-3B by 25%; no vision but good for coding; maybe run this is separate server for doing coding tasks ➡️Agents A1 4B - This one is quite interesting. Another Qwen3.5 4B base. I just learnt this right now. This model may surpassed the Ministral3-3B that I'm currently running. ➡️NeoHorse 1 4B - wait for GGUF version comes out; Qwen 3.5 4B base with vision striped ➡️Needle2 45M - need to use separately from llama.cpp server; currently testing to see if it can be used as spawning sub-agents to do parallel tasks
View all activity

Organizations

Unsloth Jobs Explorers's profile picture