What are the hardware requirements for CodeFormulaV2 Mlx Bf16?

CodeFormulaV2 Mlx Bf16 requires approximately 0.6 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed CodeFormulaV2 Mlx Bf16 and how large is it?

CodeFormulaV2 Mlx Bf16 is developed by mlx-community, a model with 315.5m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate CodeFormulaV2 Mlx Bf16?

CodeFormulaV2 Mlx Bf16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

CodeFormulaV2 Mlx Bf16 by mlx-community — VRAM 0.6GB, 8K context

Name: CodeFormulaV2 Mlx Bf16
Author: mlx-community

CodeFormulaV2 Mlx Bf16 is an open-source language model by mlx-community. Features: 315.5m LLM, VRAM: 0.6GB, Context: 8K, License: cdla-permissive-2.0, LLM Explorer Score: 0.23.

Arxiv:2408.09869 Base model:docling-project/cod... Base model:quantized:docling-p... Conversational Dataset:ds4sd/synthcodenet Dataset:ds4sd/synthformulanet En Idefics3 Image-text-to-text Mlx Mlx-vlm Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/mlx-community/CodeFormulaV2-mlx-bf16

CodeFormulaV2 Mlx Bf16 Parameters and Internals

LLM Name	CodeFormulaV2 Mlx Bf16
Repository 🤗	https://huggingface.co/mlx-community/CodeFormulaV2-mlx-bf16
Base Model(s)	CodeFormulaV2 docling-project/CodeFormulaV2
Model Size	315.5m
Required VRAM	0.6 GB
Updated	2026-10-22
Maintainer	mlx-community
Model Type	idefics3
Model Files	0.6 GB
Supported Languages	en
Model Architecture	Idefics3ForConditionalGeneration
License	cdla-permissive-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.51.3
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|pad\|>
Vocabulary Size	100480
Errors	replace

Rank the CodeFormulaV2 Mlx Bf16 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to CodeFormulaV2 Mlx Bf16

Best Alternatives	Context / RAM	Downloads	Likes
CodeFormulaV2	8K / 0.6 GB	68167	4

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/CodeFormulaV2-mlx-bf16.