JetBrains/Qwen3.8-3.6-27B-blend
Image-Text-to-Text • 28B • Updated • 1.14k • 33
Qwen3.8-3.6-27B Blend
Junie Local's unofficial JetBrains 50/50 blend of Qwen3.6-27B and Qwen3.8-27B: BF16, GGUF, and MLX weights.
Note BF16 merged checkpoint in Safetensors format.
JetBrains/Qwen3.8-3.6-27B-blend-GGUF
Image-Text-to-Text • 27B • Updated • 7.03k • 28Note IQ3_S, Q4_K_M, and Q5_K_M GGUFs with embedded MTP, plus BF16 vision.
JetBrains/Qwen3.8-3.6-27B-blend-MLX-4bit
Image-Text-to-Text • 27B • Updated • 1.13k • 9Note 4-bit MLX main model for Apple silicon; pair with the MTP drafter.
JetBrains/Qwen3.8-3.6-27B-blend-MTP-MLX-4bit
0.4B • Updated • 951 • 6Note 4-bit native MTP drafter for the matching MLX main model.