What are the hardware requirements for CuMo Mistral 7B?

CuMo Mistral 7B requires approximately 16.5 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed CuMo Mistral 7B and how large is it?

CuMo Mistral 7B is developed by shi-labs, a model with 7b 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 CuMo Mistral 7B?

CuMo Mistral 7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

CuMo Mistral 7B by shi-labs — VRAM 16.5GB, 32K context

Name: CuMo Mistral 7B
Author: shi-labs

CuMo Mistral 7B is an open-source language model by shi-labs. Features: 7b LLM, VRAM: 16.5GB, Context: 32K, License: cc-by-nc-4.0, LLM Explorer Score: 0.12.

Conversational Endpoints compatible Llava mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/shi-labs/CuMo-mistral-7b

CuMo Mistral 7B Parameters and Internals

Model Type

multimodal LLM

Use Cases

Primary Use Cases:

research on large multimodal models and chatbots

LLM Name	CuMo Mistral 7B
Repository 🤗	https://huggingface.co/shi-labs/CuMo-mistral-7b
Model Size	7b
Required VRAM	16.5 GB
Updated	2026-06-22
Maintainer	shi-labs
Model Type	llava_mistral
Model Files	4.9 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 1.6 GB: 4-of-4 0.0 GB
Model Architecture	LlavaMistralForCausalLM
License	cc-by-nc-4.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.37.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the CuMo Mistral 7B 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 CuMo Mistral 7B

Best Alternatives	Context / RAM	Downloads	Likes
Llava Med V1.5 Mistral 7B	32K / 15.1 GB	12304	125
Llava V1.6 Mistral 7B	32K / 15.1 GB	9271	246
Turkish BakLLaVa1.5 Mistral	32K / 15.3 GB	18	6
Llava Model	32K / 15.1 GB	5	0
Fc24 Mk3	32K / 20.6 GB	5	0
Fc24 Mk2	32K / 20.6 GB	5	0
LLaVA NeXT Video 7B 32K	32K / 15.1 GB	250	7
Llava Mistral 7B Finetuned	32K / 15.1 GB	15	2
Llava Mistral 7B Tokenizer	32K / GB	9	2
Llava Maid 7B DPO	32K / 14.5 GB	7	3

Note: green Score (e.g. "73.2") means that the model is better than shi-labs/CuMo-mistral-7b.