florianvoss/Qwen3-4B-DFlash-N16-LLiMa-3.0.0

Text Generation • Updated about 18 hours ago

Note Qwen3-4B target + INT8 DFlash draft; n16, 4K context, n128 prefill.

florianvoss/Llama-3.1-8B-Instruct-DFlash-N8-LLiMa-3.0.0

Text Generation • Updated 3 days ago

Note Llama-3.1-8B-Instruct target + INT8 DFlash draft; n8, 4K context, n128 prefill.

florianvoss/Qwen3-8B-DFlash-N16-LLiMa-3.0.0

Text Generation • Updated about 18 hours ago

Note Qwen3-8B target + INT8 DFlash draft; N16, 4K context, N128 prefill.

florianvoss/Qwen3.5-4B-DFlash-N16-LLiMa-3.0.0

Image-Text-to-Text • Updated about 18 hours ago

Note Qwen3.5-4B target + INT8 DFlash draft; N16, 4K context, N128 prefill. 448×448 vision.

florianvoss/Qwen3.5-9B-DFlash-N16-LLiMa-3.0.0

Image-Text-to-Text • Updated about 18 hours ago

Note Qwen3.5-9B target + INT8 DFlash draft; N16, 4K context, N128 prefill. 448×448 vision.