Florian Voss

florianvoss's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated 2 collections 5 days ago

Vision-Language Models

Collection

Precompiled vision-language models for on-device multimodal tasks. • 21 items • Updated 5 days ago • 2

Large Language Models

Collection

Precompiled language models for on-device text generation. • 31 items • Updated 5 days ago • 1

updated 8 models 5 days ago

simaai/gemma-4-E2B-it-GPTQ-MTP-a16w4

Image-Text-to-Text • Updated 5 days ago

simaai/gemma-4-E4B-it-GPTQ-MTP-a16w4

Image-Text-to-Text • Updated 5 days ago

simaai/Gemma-4-E2B-it-TextOnly-GPTQ-MTP-a16w4

Text Generation • Updated 5 days ago

simaai/Gemma-4-E4B-it-TextOnly-GPTQ-MTP-a16w4

Text Generation • Updated 5 days ago

simaai/Llama-3.1-Swallow-8B-Instruct-v0.5-GPTQ-DFlash-a16w4

Text Generation • Updated 5 days ago

simaai/Qwen3-4B-Autoround-DFlash-a16w4

Text Generation • Updated 5 days ago

simaai/Llama-3.1-8B-Instruct-GPTQ-DFlash-a16w4

Text Generation • Updated 5 days ago

simaai/Qwen3-8B-GPTQ-DFlash-a16w4

Text Generation • Updated 5 days ago

updated a collection 5 days ago

Pre-Quantized Models

Collection

Pre-quantized safetensor models (GPTQ/AutoRound) and their optimization scripts, ready to be compiled for SiMa.ai hardware. • 48 items • Updated 5 days ago

updated a model 5 days ago

simaai/Llama-3.1-Swallow-8B-Instruct-v0.5-DFlash-RTN-INT8-Safetensors

1B • Updated 5 days ago • 30