Article
funes: Local Memory for Coding Agents, Built on Lance
ariG23498
• • 6
🦥 unsloth my mind
MadMike
MadMike477
AI & ML interests
AI/ML and tech enthusiast, training & fine-tuning models 🦥💚
OSS supporter & Love helping people and always looking to learn, build, and contribute💚
<3
Recent Activity
upvoted an article about 8 hours ago
funes: Local Memory for Coding Agents, Built on Lance liked a Space 3 days ago
ariG23498/flow-matching reacted to sergiopaniego's post with 👀 6 days ago
while preparing the last class of the Training Agents live series during the summer, i spent some time reading the post-training sections of many frontier model reports, to learn how they use RL environments to improve their models, and wrote a blog about it
if you use any kind of coding harness, or you saw the Blender scenes that went viral recently, this might be interesting to you
Blog: https://huggingface.co/blog/sergiopaniego/rl-environments-2026Organizations
upvoted an article about 8 hours ago
liked a
Space 3 days ago
reacted to sergiopaniego's post with 👀 6 days ago
Post
3106
while preparing the last class of the Training Agents live series during the summer, i spent some time reading the post-training sections of many frontier model reports, to learn how they use RL environments to improve their models, and wrote a blog about it
if you use any kind of coding harness, or you saw the Blender scenes that went viral recently, this might be interesting to you
Blog: https://huggingface.co/blog/sergiopaniego/rl-environments-2026
if you use any kind of coding harness, or you saw the Blender scenes that went viral recently, this might be interesting to you
Blog: https://huggingface.co/blog/sergiopaniego/rl-environments-2026
liked a
dataset 6 days ago
upvoted an article 6 days ago
Article
One sandbox per rollout, or how labs run RL for agents in 2026
sergiopaniego
• • 10 liked a
Space 7 days ago
liked a
Space 8 days ago
reacted to OppaAI's post with 🔥 8 days ago
Post
3154
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
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
- 7 replies
reacted to danielhanchen's post with 🔥🚀 9 days ago
Post
4255
Qwen3.8-27B Unsloth GGUF is now the #1 most-liked GGUF of all time! 🤗🦥
The model hit 10M downloads and 3.7K likes in just 24 days on Hugging Face - all thanks to you.
GGUF: unsloth/Qwen3.8-27B-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.8
The model hit 10M downloads and 3.7K likes in just 24 days on Hugging Face - all thanks to you.
GGUF: unsloth/Qwen3.8-27B-GGUF
Guide: https://unsloth.ai/docs/models/qwen3.8
- 5 replies
liked a
model 11 days ago
liked a
model 12 days ago
liked 3
models 14 days ago
upvoted an article 14 days ago
Article
Training a coding model to paint watercolours with TRL and OpenEnv
sergiopaniego
• • 68 liked 3
models 16 days ago
