Beta

Explore
Marketplace
Neural Labs
Chat
Wallet
Docs

Beta

Explore Marketplace Neural Labs Wallet Docs

Build

Manage

My assets Manage wallet Organization

Community

Discord X (Twitter)Telegram

Docs Privacy Policy Terms and Conditions

Proud member of

Proud member of

Docs Cookie Policy

Privacy Policy Terms and Conditions

© 2026 AlphaNeural AI. All rights reserved.

Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit – AI Model by shamsghi | AlphaNeural AI

You can deploy this model and start earning money today!

shamsghi/
Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit

like

0

image-text-to-text

text-generation-inference

Ali-Yaser/KIMI-K2.5-450000x-ShareGPT

allenai/tulu-3-sft-mixture

nohurry/Opus-4.6-Reasoning-3000x-filtered

ertghiu256/Qwen3.5-2b-Kimi-and-Opus-Distillation

Views

No views yet

Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit

This is an MLX 8-bit conversion of ertghiu256/Qwen3.5-2b-Kimi-and-Opus-Distillation for Apple Silicon.

Model Details

Base model: ertghiu256/Qwen3.5-2b-Kimi-and-Opus-Distillation
Format: MLX safetensors
Runtime: mlx-vlm
Quantization: 8-bit
License: Apache-2.0

Release Notes

v1.0.0 - 2026-04-15

Initial MLX 8-bit release.
Converted from the original Hugging Face checkpoint to MLX format.
Includes tokenizer and processor config files.
Verified locally after conversion.

Usage

bash

mlx_vlm.generate \
  --model shamsghi/Qwen3.5-2b-Kimi-and-Opus-Distillation-MLX-8bit \
  --prompt "Write a short hello world in Python." \
  --max-tokens 100