Precompiled language models for on-device text generation.
SiMa.ai
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
SiMa.ai | Scaling Physical AI at the Edge
SiMa.ai provides a purpose-built platform for deploying high-performance AI models for vision, audio, and generative applications at the edge with industry-leading power efficiency.
Download our pre-optimized, ready-to-deploy models for the Modalix™ MLSoC below.
- Vision-Language (VLMs): Gemma 3, Qwen2.5-VL, Qwen3-VL, and LFM2-VL.
- Large-Language (LLMs): Llama 3.2/3.1, Phi-3.5-mini, and Mistral-7B, Qwen2.5/3, Gemma
- Audio & Speech: Whisper
Deployment & Tools
- Models are optimized using LLiMa (Automated Code Generation) for sub-10W inference.
- Deployment supports a16w4 and Hybrid a16w8/4 quantization to maximize Performance-per-Watt.
- Join our Developer Portal or visit our Documentation for documentation and SDK access.
models 95
simaai/testing_Llama
Updated
simaai/Qwen2.5-VL-7B-Instruct-GPTQ-Safetensors
Image-Text-to-Text • 5B • Updated • 37
simaai/LFM2.5-VL-450M-Autoround-Safetensors
Image-Text-to-Text • 0.5B • Updated • 29
simaai/Qwen2.5-VL-3B-Instruct-GPTQ-Safetensors
Image-Text-to-Text • 3B • Updated • 21
simaai/Qwen3-VL-2B-Instruct-GPTQ-Safetensors
Image-Text-to-Text • 2B • Updated • 20
simaai/Qwen3-VL-4B-Instruct-Autoround-Safetensors
Image-Text-to-Text • 5B • Updated • 31
simaai/Qwen3-VL-8B-Instruct-GPTQ-Safetensors
Image-Text-to-Text • 9B • Updated • 271
simaai/Llama-3.1-Swallow-8B-Instruct-v0.5-GPTQ-Safetensors
Text Generation • 8B • Updated • 51
simaai/LFM2-VL-1.6B-Autoround-Safetensors
Image-Text-to-Text • 2B • Updated • 34
simaai/LFM2-VL-3B-Autoround-Safetensors
Image-Text-to-Text • 3B • Updated • 25
datasets 0
None public yet