openfree/Darwin-Qwen3-4B
4B • Updated • 21 • 12
openfree
openfree
AI & ML interests
Contact: arxivgpt@gmail.com
Recent Activity
reacted to SeaWolf-AI's post with 👍 about 16 hours ago
No GPU. No cloud. Just your phone.
Most “small” models still beg for a datacenter. Ours fit in your pocket.
VIDRAFT POCKET is a family of GGUF models that run on an iPhone and on a GPU-free PC, straight out of the box with llama.cpp, Ollama, LM Studio, and PocketPal. Seven weeks after launch they crossed 1 million downloads. Today the family is past 2.81 million and still climbing, every day.
Three models, one pocket:
🟢 POCKET-35B — a 35B mixture-of-experts that runs on an iPhone and on a PC with no GPU. Balanced power.
→ https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF
🔵 POCKET-26B — a Gemma-4 based 26B MoE, tuned for on-device Korean. Lightweight and fast.
→ https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF
🟣 POCKET-Darwin-180B — a 180B flagship running on a laptop in 4-bit GGUF. The datacenter, on your desk.
→ https://huggingface.co/FINAL-Bench/POCKET-Darwin-180B-GGUF
The whole family lives here: https://huggingface.co/FINAL-Bench
Try our models live in the browser: https://huggingface.co/spaces/FINAL-Bench/POCKET-Image-Studio
Private by default. Offline by design. Yours to run.
#OnDeviceAI #LocalLLM #llamacpp #GGUF #VIDRAFT #POCKET reacted to SeaWolf-AI's post with 🧠 about 16 hours ago
No GPU. No cloud. Just your phone.
Most “small” models still beg for a datacenter. Ours fit in your pocket.
VIDRAFT POCKET is a family of GGUF models that run on an iPhone and on a GPU-free PC, straight out of the box with llama.cpp, Ollama, LM Studio, and PocketPal. Seven weeks after launch they crossed 1 million downloads. Today the family is past 2.81 million and still climbing, every day.
Three models, one pocket:
🟢 POCKET-35B — a 35B mixture-of-experts that runs on an iPhone and on a PC with no GPU. Balanced power.
→ https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF
🔵 POCKET-26B — a Gemma-4 based 26B MoE, tuned for on-device Korean. Lightweight and fast.
→ https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF
🟣 POCKET-Darwin-180B — a 180B flagship running on a laptop in 4-bit GGUF. The datacenter, on your desk.
→ https://huggingface.co/FINAL-Bench/POCKET-Darwin-180B-GGUF
The whole family lives here: https://huggingface.co/FINAL-Bench
Try our models live in the browser: https://huggingface.co/spaces/FINAL-Bench/POCKET-Image-Studio
Private by default. Offline by design. Yours to run.
#OnDeviceAI #LocalLLM #llamacpp #GGUF #VIDRAFT #POCKET reacted to SeaWolf-AI's post with 😎 about 16 hours ago
No GPU. No cloud. Just your phone.
Most “small” models still beg for a datacenter. Ours fit in your pocket.
VIDRAFT POCKET is a family of GGUF models that run on an iPhone and on a GPU-free PC, straight out of the box with llama.cpp, Ollama, LM Studio, and PocketPal. Seven weeks after launch they crossed 1 million downloads. Today the family is past 2.81 million and still climbing, every day.
Three models, one pocket:
🟢 POCKET-35B — a 35B mixture-of-experts that runs on an iPhone and on a PC with no GPU. Balanced power.
→ https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF
🔵 POCKET-26B — a Gemma-4 based 26B MoE, tuned for on-device Korean. Lightweight and fast.
→ https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF
🟣 POCKET-Darwin-180B — a 180B flagship running on a laptop in 4-bit GGUF. The datacenter, on your desk.
→ https://huggingface.co/FINAL-Bench/POCKET-Darwin-180B-GGUF
The whole family lives here: https://huggingface.co/FINAL-Bench
Try our models live in the browser: https://huggingface.co/spaces/FINAL-Bench/POCKET-Image-Studio
Private by default. Offline by design. Yours to run.
#OnDeviceAI #LocalLLM #llamacpp #GGUF #VIDRAFT #POCKETOrganizations
openfree/adsd1
7B • Updated • 8
openfree/Qwen2.5-Mistral-7B-Instr
8B • Updated • 15
openfree/TinyLlama-SmolLM
1B • Updated • 7
openfree/Qwen2.5-Mistral-7B
Updated
openfree/dasdsds2
7B • Updated • 8
openfree/WizardMath-AgentEvol-7B
7B • Updated • 26
openfree/WizardMath-AgentEvol
7B • Updated • 9
openfree/gpt2-bert
0.1B • Updated • 8
openfree/DarwinAI-gemma-3-270m
0.3B • Updated • 13 • 1
openfree/Gemma-3-R1984-1B-0613
1.0B • Updated • 3
openfree/Gemma-3-R1984-4B
Image-Text-to-Text • 4B • Updated • 16 • 1
openfree/Gemma-3-R1984-1B
Image-Text-to-Text • 1.0B • Updated • 9
openfree/flux-chatgpt-ghibli-lora
Text-to-Image • Updated • 278 • • 510
openfree/leonardo-dicaprio
Text-to-Image • Updated • 21 • • 26
openfree/lee-min-ho
Text-to-Image • Updated • 11 • • 25
openfree/sergey-lazarev
Text-to-Image • Updated • 4 •
openfree/bruce-lee
Text-to-Image • Updated • 24 • • 26
openfree/winslow-homer
Text-to-Image • Updated • 36 • • 39
openfree/van-gogh
Text-to-Image • Updated • 45 • • 41
openfree/paul-cezanne
Text-to-Image • Updated • 46 • • 41
openfree/pierre-auguste-renoir
Text-to-Image • Updated • 56 • • 40
openfree/claude-monet
Text-to-Image • Updated • 207 • • 235
openfree/myt-flux-fantasy
Text-to-Image • Updated • 22 • • 20
openfree/QwQ-R1984-32B-Q4_K_M-GGUF
33B • Updated • 42 • 129
openfree/QwQ-R1984-32B-Q8_0-GGUF
33B • Updated • 34 • 125
openfree/QwQ-32B-Q4_K_M-GGUF
Text Generation • 33B • Updated • 45 • 98
openfree/Qwen2.5-VL-32B-Instruct-Q4_K_M-GGUF
Image-Text-to-Text • 33B • Updated • 832 • 113
openfree/Qwen2.5-VL-32B-Instruct-Q8_0-GGUF
Image-Text-to-Text • 33B • Updated • 165 • 109
openfree/QwQ-32B-Q8_0-GGUF
Text Generation • 33B • Updated • 23 • 104