EXL3 quantization of ukisai/Swift-Qwen3.8-27b, UkisAI's reasoning-efficient derivative of Qwen3.8-27B, using 58.3% fewer thinking tokens while maintaining near-identical performance (<1% loss) and as a result getting a x1.95 speed-up on several tasks. 13.9 GB of weights — sized to leave room for large KV caches on 24 GB GPUs: with the built-in MTP draft head the full native 262k context fits fully resident.

Quantization details

setting value
format EXL3 v1.5.0 (quantization_config.json)
average bits 3.5 bpw (module-adaptive)
head bits 6 (default)
high-quality mode (-hq) no

The conversion was done with this simple command:

python3 convert.py \
  -i /mnt/d/models/ukisai/Swift-Qwen3.8-27B \
  -o /mnt/d/models/charnet3d/Swift-Qwen3.8-27B-Exl3-3.5bpw \
  -w /mnt/d/temp_scratchpad \
  -b 3.5

This is shared as-is to save time for others who need it.

No accuracy testing or quality benchmarks were done, except normal usage which seemed fine.

The creator is not liable if this model nuked your house or deleted your prod db.

Requirements

  • exllamav3 — the qwen3_5 architecture used here is supported upstream, including MTP speculative decoding; no fork required for basic inference on x86 CUDA GPUs.

License

swift-open-license-1.0, inherited from the base model.

Credits

Downloads last month
157
Safetensors
Model size
7B params
Tensor type
BF16
·
F16
·
I16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for charnet3d/Swift-Qwen3.8-27B-Exl3-3.5bpw

Base model

Qwen/Qwen3.8-27B
Quantized
(55)
this model