Subscribe and Support
This is Qwen/Qwen3.8-27B quantized with AutoRound. Model packed by llm-compressor.
Quantization ("balanced" settings):
- INT data types
- ~3.5 bits for linear layers
- 8-bit LM head
- BF16 MTP layers
- 8-bit activations
The model is compatible with vLLM (tested: v0.26+). Made and Tested with an RTX Pro 6000 (Google Colab's G4). Currently under evaluation: Subscribe to be notified when I publish the results.
- Made by: The Kaitchup
Instructions
vllm serve [this_model_id] \
--tensor-parallel-size 1 \
--enable-auto-tool-choice \
--tool-call-parser qwen3_coder \
--reasoning-parser qwen3
Add --speculative-config '{"method":"mtp","num_speculative_tokens":X}' for MTP, where good values for X are between 2 and 6 (depending on your tasks and concurrency).