ornith-ai-Ornith-1.5-9B-MTPLX

MTPLX-branded multi-token-prediction model for Apple Silicon (MLX). Forged with MTPLX Forge from ornith-ai/Ornith-1.5-9B. On Apple M1 Pro 32GB

Verification

  • Best depth: D1
  • Multiplier vs autoregressive baseline: 1.57脳
  • Verified on: Apple M1 Pro
  • Sampler: temperature 0.6 路 top_p 0.95 路 top_k 20

See mtplx_runtime.json for the full verification record.

Usage

# MTPLX picks this model up automatically when downloaded:
mtplx pull Artie101/ornith-ai-Ornith-1.5-9B-8bit-MTPLX
mtplx start chat

License

See LICENSE.

Downloads last month
-
Safetensors
Model size
3B params
Tensor type
F16
U32
BF16
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for Artie101/Ornith-1.5-9B-8bit-MTPLX

Quantized
(71)
this model