airagrp
/

Qwen3.8-27B-MTP-bf16

Model card Files Files and versions

Qwen3.8-27B-MTP-bf16

This is MTP head only full model at airagrp/Qwen3.8-27B-bf16

Get around 20tps on M5 max

Downloads last month: 212

Safetensors

Model size

0.4B params

Tensor type

BF16

·

MLX

Hardware compatibility

Log In to add your hardware

Quantized

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for airagrp/Qwen3.8-27B-MTP-bf16

Base model

Qwen/Qwen3.8-27B

Finetuned

(273)

this model

Collection including airagrp/Qwen3.8-27B-MTP-bf16

Qwen3.8-27B

8 items • Updated 6 days ago