TokenRhythmAdmin

AI & ML interests

None yet

Recent Activity

updated a Space 3 days ago

reacted to OppaAI's post with 🔥 3 days 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

upvoted a collection 4 days ago

NeoHorse-1-GGUF

View all activity

Organizations

updated a Space 3 days ago

README

👁

reacted to OppaAI's post with 🔥 3 days ago

Post

3148

Another small 4B model comes out yesterday.
NeoHorse 1 4B
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