Swift 1.5 Qwen3.8-Flash-Next GSQ-RCO abliterated โ€” IQ3_S (3-Shard Distribution)

Re-sharded version of SC117/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF split into 3 shards specifically designed for constrained-storage environments (such as Kaggle / Colab with limited working partitions):

Shard File Size Tensors
Swift-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-00001-of-00003.gguf 44.85 GB 373
Swift-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-00002-of-00003.gguf 13.71 GB 329
Swift-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-00003-of-00003.gguf 23.98 GB 522
Total 83.54 GB 1,224

Highlights

  • 100% bit-exact: Identical quantization weights as SC117 / UkisAI Swift 1.5 GSQ-RCO.
  • Kaggle / Constrained-disk Ready: Shard 2 is under 15 GB to easily fit in /kaggle/working while Shards 1 & 3 fit within /tmp (< 70 GB).
  • Native support in Strata and llama.cpp.
Downloads last month
451
GGUF
Model size
177B params
Architecture
qwen4exp
Hardware compatibility
Log In to add your hardware

3-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for dsfsfdff/Swift-1.5-Qwen3.8-Flash-Next-GSQ-RCO-abliterated-IQ3_S-GGUF