DeepSeek-V4-Flash-MLX-Q2-mixed-gs128-affine is an open-weight text-generation model published by Thump604 on the Hugging Face Hub. It has 619 downloads. Runs with mlx.

Author

Thump604

Platform

api

Pricing model

free

Capabilities

Text generation
Library: mlx

Related llms

Others in the same category, ranked by how often they are opened.

Meta-Llama-3-8B8B open-weight LLM by meta-llamaLLMs · Writing
Mistral-7B-v0.17B open-weight LLM by mistralaiLLMs · Writing
gpt2Open-weight LLM by openai-communityLLMs · Writing
gemma-7b7B open-weight LLM by googleLLMs · Writing
Llama-3.2-1B1B open-weight LLM by meta-llamaLLMs · Writing
VibeVoice-1.5B1.5B open-weight LLM by microsoftLLMs · Writing
grok-1Open-weight LLM by xai-orgLLMs · Writing
Llama-3.1-8B8B open-weight LLM by meta-llamaLLMs · Writing

DeepSeek-V4-Flash-MLX-Q2-mixed-gs128-affine

Description

Author

Platform

Pricing model

Categories

Tags

Capabilities