What are the hardware requirements for GML Mistral Merged V1?

GML Mistral Merged V1 requires approximately 18 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 GML Mistral Merged V1 and how large is it?

GML Mistral Merged V1 is developed by mlabonne, a model with 9b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does GML Mistral Merged V1 perform on standard benchmarks?

GML Mistral Merged V1 has the following published scores: MMLU 64.13. Compare against reference models on this page or on the LLM Explorer leaderboards.

GML Mistral Merged V1 by mlabonne — VRAM 18GB, 32K context

Name: GML Mistral Merged V1
Author: mlabonne

GML Mistral Merged V1 is an open-source language model by mlabonne. Features: 9b LLM, VRAM: 18GB, Context: 32K, License: apache-2.0, Merged, LLM Explorer Score: 0.13, Arc: 43.8, HellaSwag: 57.9, MMLU: 64.1.

Merged Model Endpoints compatible Mistral Model-index Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlabonne/GML-Mistral-merged-v1

GML Mistral Merged V1 Parameters and Internals

Model Type

text-generation

Additional Notes

This model is a merge of the following models made with mergekit: [quantumaikr/quantum-v0.01](https://huggingface.co/quantumaikr/quantum-v0.01), [mncai/mistral-7b-dpo-v5](https://huggingface.co/mncai/mistral-7b-dpo-v5) with the configuration using slice sources from both models and a passthrough merge method in bfloat16 dtype.

LLM Name	GML Mistral Merged V1
Repository 🤗	https://huggingface.co/mlabonne/GML-Mistral-merged-v1
Merged Model	Yes
Model Size	9b
Required VRAM	18 GB
Updated	2026-08-05
Maintainer	mlabonne
Model Type	mistral
Model Files	9.9 GB: 1-of-2 8.1 GB: 2-of-2
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.35.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the GML Mistral Merged V1 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 GML Mistral Merged V1

Best Alternatives	Context / RAM	Downloads	Likes
Peagle 9B	32K / 18 GB	12814	0
MetaMath Mistral Pro	32K / 17.9 GB	18	6
Peagle 9B	32K / 18 GB	8203	0
...onarch Neurotic 9B Passthrough	32K / 17.9 GB	82	0
Mistral 9B Instruct	32K / 35.9 GB	7	0
Garbage 9B	32K / 17.9 GB	72	3
Bepis 9B	32K / 18 GB	100	6
Mistral 9B Instruct V0.2	32K / 17.9 GB	89	3
Notus TheTop 7B Passthrough	32K / 18 GB	5	0
...raAI Foredoomed 9B EXL 2.8 Bpw	32K / 3.7 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than mlabonne/GML-Mistral-merged-v1.