AI is happening. The future is updating.Qwen3.8-27B-TQ
Qwen3.8-27B for the tqLLM engine in four sizes (11.85 to 14.72 GB), with a DFlash2 draft model for exact speculative decoding. TQ_XS and TQ_S target 16 GB GPUs; TQ_L targets 24 GB GPUs and GB10. For another size, replace `Qwen3.8-27B-TQ_S.gguf` with `Qwen3.8-27B-TQ_XS.gguf`, `Qwen3.8-27B-TQ_M.gguf` or `Qwen3.8-27B-TQ_L.gguf` (also in `MODEL_FILE` below). These files need tqLLM: their TQ3 / TQ4 tensors use tqLLM's own GGUF types (300, 301), so stock llama.cpp, Ollama and LM Studio cannot load them.
Qwen3.8-27B for the tqLLM engine in four sizes (11.85 to 14.72 GB), with a DFlash2 draft model for exact speculative decoding. TQ_XS and TQ_S target 16 GB GPUs; TQ_L targets 24 GB GPUs and GB10. For another size, replace `Qwen3.8-27B-TQ_S.gguf` with `Qwen3.8-27B-TQ_XS.gguf`, `Qwen3.8-27B-TQ_M.gguf` or `Qwen3.8-27B-TQ_L.gguf` (also in `MODEL_FILE` below). These files need tqLLM: their TQ3 / TQ4 tensors use tqLLM's own GGUF types (300, 301), so stock llama.cpp, Ollama and LM Studio cannot load them.