What are the hardware requirements for Mistral 4B FT 2?

Mistral 4B FT 2 requires approximately 7.5 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 Mistral 4B FT 2 and how large is it?

Mistral 4B FT 2 is developed by fhai50032, a model with 4b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Mistral 4B FT 2 perform on standard benchmarks?

Mistral 4B FT 2 has the following published scores: MMLU 25.46. Compare against reference models on this page or on the LLM Explorer leaderboards.

Mistral 4B FT 2 by fhai50032 — VRAM 7.5GB, 32K context

Name: Mistral 4B FT 2
Author: fhai50032

Mistral 4B FT 2 is an open-source language model by fhai50032. Features: 4b LLM, VRAM: 7.5GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.16, Arc: 25.9, HellaSwag: 39.6, MMLU: 25.5, GSM8K: 2.9.

Arxiv:1910.09700 Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/fhai50032/Mistral-4B-FT-2

Mistral 4B FT 2 Parameters and Internals

LLM Name	Mistral 4B FT 2
Repository 🤗	https://huggingface.co/fhai50032/Mistral-4B-FT-2
Model Size	4b
Required VRAM	7.5 GB
Updated	2026-07-05
Maintainer	fhai50032
Model Type	mistral
Model Files	4.9 GB: 1-of-2 2.6 GB: 2-of-2
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.38.2
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Rank the Mistral 4B FT 2 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 Mistral 4B FT 2

Best Alternatives	Context / RAM	Downloads	Likes
GenomeOcean 4B V1.2	32K / 8.5 GB	71	1
GenomeOcean 4B	32K / 8.5 GB	857	11
Ministral 4B Fork	32K / 9 GB	9	0
Ministral 4B Instruct	32K / 8.9 GB	100	8
MistralPh3 4B Slerp	4K / 7.8 GB	6	0
...mail Search Phi3 Vllm Model 4b	4K / 2.3 GB	7	0
Athena CodePhi 4B 4K V0.1	4K / 7.6 GB	19	1

Note: green Score (e.g. "73.2") means that the model is better than fhai50032/Mistral-4B-FT-2.