What are the hardware requirements for Bophades Mistral Math DPO 7B?

Bophades Mistral Math DPO 7B requires approximately 14.4 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 Bophades Mistral Math DPO 7B and how large is it?

Bophades Mistral Math DPO 7B is developed by nbeerbower, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Bophades Mistral Math DPO 7B perform on standard benchmarks?

Bophades Mistral Math DPO 7B has the following published scores: MMLU 64.62. Compare against reference models on this page or on the LLM Explorer leaderboards.

Bophades Mistral Math DPO 7B by nbeerbower — VRAM 14.4GB, 32K context

Name: Bophades Mistral Math DPO 7B
Author: nbeerbower

Bophades Mistral Math DPO 7B is an open-source language model by nbeerbower. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.12, Arc: 73, HellaSwag: 89, MMLU: 64.6, GSM8K: 69.5.

Base model:finetune:nbeerbower... Base model:nbeerbower/bophades... Dataset:kyujinpy/orca math dpo Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/nbeerbower/bophades-mistral-math-DPO-7B

Bophades Mistral Math DPO 7B Parameters and Internals

Model Type

text generation

Use Cases

Primary Use Cases:

Research and experimentation in text generation

Additional Notes

Fine-tuned model for math-specific tasks using the Orca Math DPO dataset.

Training Details

Data Sources:

kyujinpy/orca_math_dpo

Methodology:

Fine-tuned using Direct Preference Optimization (DPO)

Hardware Used:

A100 on Google Colab

Model Architecture:

LoRA with target modules k_proj, gate_proj, v_proj, up_proj, q_proj, o_proj, down_proj

LLM Name	Bophades Mistral Math DPO 7B
Repository 🤗	https://huggingface.co/nbeerbower/bophades-mistral-math-DPO-7B
Base Model(s)	Bophades V2 Mistral 7B nbeerbower/bophades-v2-mistral-7B
Model Size	7b
Required VRAM	14.4 GB
Updated	2026-07-19
Maintainer	nbeerbower
Model Type	mistral
Model Files	4.9 GB: 1-of-3 5.0 GB: 2-of-3 4.5 GB: 3-of-3
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Bophades Mistral Math DPO 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 Bophades Mistral Math DPO 7B

Best Alternatives	Context / RAM	Downloads	Likes
...Nemo Instruct 2407 Abliterated	1000K / 24.5 GB	220	20
MegaBeam Mistral 7B 512K	512K / 14.4 GB	8470	54
SpydazWeb AI HumanAI RP	512K / 14.4 GB	16	1
SpydazWeb AI HumanAI 002	512K / 14.4 GB	18	1
...daz Web AI ChatML 512K Project	512K / 14.5 GB	12	0
MegaBeam Mistral 7B 300K	282K / 14.4 GB	3779	16
MegaBeam Mistral 7B 300K	282K / 14.4 GB	8018	17
Hebrew Mistral 7B 200K	256K / 30 GB	23	15
Astral 256K 7B	250K / 14.4 GB	9	0
Astral 256K 7B V2	250K / 14.4 GB	8	0

Note: green Score (e.g. "73.2") means that the model is better than nbeerbower/bophades-mistral-math-DPO-7B.