35B-A3B MoE MTP Vision for 24 GB GPUs Collection 35B-A3B mixture-of-experts models in EXL3 4.00bpw for one 24 GB GPU, with vision and MTP. Served with vLLM and our EXL3 plugin. • 5 items • Updated 4 days ago
27B Dense MTP Vision for 24 GB GPUs Collection Qwen3.8-27B family quantized for one 24 GB GPU, with vision and MTP. Tested as a Spanish-language Linux sysadmin agent (opencode + vLLM). • 16 items • Updated 4 days ago
Speculative-decoding drafts Collection Draft models that speed up our models with speculative decoding. The output is the same as the target model's. • 2 items • Updated 12 days ago
Sysadmin agent models: our picks Collection What we actually run, one per GPU size, for a Spanish-language Linux sysadmin agent with opencode. • 7 items • Updated 12 days ago
27B Visual Reasoning for 16-24 GB GPUs Collection 27B vision-language models for visual reasoning over the full image (no MTP), quantized for one 16 GB or 24 GB GPU. • 2 items • Updated 17 days ago
27B Visual Reasoning for 16-24 GB GPUs Collection 27B vision-language models for visual reasoning over the full image (no MTP), quantized for one 16 GB or 24 GB GPU. • 2 items • Updated 17 days ago
27B Dense MTP Vision for 24 GB GPUs Collection Qwen3.8-27B family quantized for one 24 GB GPU, with vision and MTP. Tested as a Spanish-language Linux sysadmin agent (opencode + vLLM). • 16 items • Updated 4 days ago