What are the hardware requirements for Mistral Ft Optimized 1218?

Mistral Ft Optimized 1218 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 Mistral Ft Optimized 1218 and how large is it?

Mistral Ft Optimized 1218 is developed by OpenPipe, 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 Mistral Ft Optimized 1218 perform on standard benchmarks?

Mistral Ft Optimized 1218 has the following published scores: MMLU 64.99. Compare against reference models on this page or on the LLM Explorer leaderboards.

Mistral Ft Optimized 1218 by OpenPipe — VRAM 14.4GB, 32K context

Name: Mistral Ft Optimized 1218
Author: OpenPipe

Mistral Ft Optimized 1218 is an open-source language model by OpenPipe. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: cc-by-nc-4.0, LLM Explorer Score: 0.12, Arc: 67.9, HellaSwag: 86.3, MMLU: 65, GSM8K: 72.3.

En Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/OpenPipe/mistral-ft-optimized-1218

Mistral Ft Optimized 1218 Parameters and Internals

Model Type

text generation

Use Cases

Areas:

Downstream fine-tuning

Primary Use Cases:

Strong base for downstream tasks

Additional Notes

Built using Weyaxi and Q-bert model slices for improved base capabilities.

Supported Languages

en (full proficiency)

Training Details

Data Sources:

Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp, Q-bert/MetaMath-Cybertron-Starling

Methodology:

Version created using Mergekit with method 'slerp' and parameters 'bfloat16'. Optimized for fine-tuning.

Release Notes

Version:

12/27/2023

Date:

12/27/2023

Notes:

Release of an updated version with similar performance and a more permissive license. Recommended for most users over this model.

LLM Name	Mistral Ft Optimized 1218
Repository 🤗	https://huggingface.co/OpenPipe/mistral-ft-optimized-1218
Model Size	7b
Required VRAM	14.4 GB
Updated	2026-07-16
Maintainer	OpenPipe
Model Type	mistral
Model Files	9.9 GB: 1-of-2 4.5 GB: 2-of-2
Supported Languages	en
Model Architecture	MistralForCausalLM
License	cc-by-nc-4.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.36.0
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Mistral Ft Optimized 1218 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

Quantized Models of the Mistral Ft Optimized 1218

Model	Likes	Downloads	VRAM
Excelpdf	0	180	25 GB
Mistral Ft Optimized 1218 GGUF	0	264	2 GB
Mistral Ft Optimized 1218 GGUF	22	466	3 GB
Mistral Ft Optimized 1218 GPTQ	4	5	4 GB
Mistral Ft Optimized 1218 AWQ	0	10	4 GB

Best Alternatives to Mistral Ft Optimized 1218

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 OpenPipe/mistral-ft-optimized-1218.