Hugging Face's logo

Collections

Discover the best community collections!

Collections trending this week
35B-A3B MoE MTP Vision for 24 GB GPUs
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.
125B-A6B MoE Flash Next MTP Vision for 48-96 GB GPUs
Qwen3.8 Flash-Next in EXL3 + n-gram embeddings. 48 GB or 96 GB, 262k context. vLLM on Ada/Blackwell, TabbyAPI on Ampere.
27B Dense MTP Vision for 24 GB GPUs
Qwen3.8-27B family quantized for one 24 GB GPU, with vision and MTP. Tested as a Spanish-language Linux sysadmin agent (opencode + vLLM).
Sysadmin agent models: our picks
What we actually run, one per GPU size, for a Spanish-language Linux sysadmin agent with opencode.
27B Dense MTP Vision for 24 GB GPUs
Qwen3.8-27B family quantized for one 24 GB GPU, with vision and MTP. Tested as a Spanish-language Linux sysadmin agent (opencode + vLLM).
35B-A3B MoE MTP Vision for 24 GB GPUs
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.
125B-A6B MoE Flash Next MTP Vision for 48-96 GB GPUs
Qwen3.8 Flash-Next in EXL3 + n-gram embeddings. 48 GB or 96 GB, 262k context. vLLM on Ada/Blackwell, TabbyAPI on Ampere.
Sysadmin agent models: our picks
What we actually run, one per GPU size, for a Spanish-language Linux sysadmin agent with opencode.