See IQuest-Coder-V1-40B-Loop-Instruct MLX in action - demonstration video

q6.5bit mixed quant typically achieves 1.128 perplexity in our testing

Quantization Perplexity
q2.5 41.293
q3.5 1.900
q4.5 1.168
q4.8 1.140
q5.5 1.141
q6.5 1.128
q8.5 1.128

Usage Notes

Tested on a M3 Ultra using Inferencer app v1.9.1

  • Single inference ~9 tokens/s @ 1000 tokens
  • Batched inference ~14 total tokens/s across two inferences
  • Memory usage: ~30 GB
Quantized with a modified version of MLX 0.30
For more details see demonstration video or visit IQuest-Coder-V1-40B-Instruct.
Downloads last month
445
Safetensors
Model size
40B params
Tensor type
BF16
·
U32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support