Qwen 3.8 27B
Running the Qwen3.8-27B model
- HyperQwen : Qwen3.8-27B on a single 24 GB card with vLLM.
- MiaAI-Lab for one 16-24 GB GPU using the EXL3 quantization format.
- MiaAI-Lab (DGX Spark) on one DGX Spark.
- ninfer, a C++/CUDA inference engine for explicitly registered Qwen checkpoints on a single NVIDIA GeForce RTX 5090.
- ninfer-3090 : an
ninferfork for RTX 3090. - ninfer-4090 : an
ninfer-3090fork for RTX 4090. - MegaCapybara : a fast inference engine for Qwen3.8-27B on the NVIDIA RTX 5090.
Running with llama.cpp or GGUF-compatible engines:
- ISTA: GSQ-RCO : small quants of ISTA lab.
- Swift-1.5-Qwen3.8-27b : UkisAI’s reasoning-efficient derivative of Qwen3.8-27B.
- Unsloth Qwen3.8-27b
Last updated on