What are the hardware requirements for Mistral Small 24B New Params 16bit?

Mistral Small 24B New Params 16bit requires approximately 47.3 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 Small 24B New Params 16bit and how large is it?

Mistral Small 24B New Params 16bit is developed by WasamiKirua, a model with 24b 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 Mistral Small 24B New Params 16bit?

Mistral Small 24B New Params 16bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mistral Small 24B New Params 16bit by WasamiKirua — VRAM 47.3GB, 32K context

Name: Mistral Small 24B New Params 16bit
Author: WasamiKirua

Mistral Small 24B New Params 16bit is an open-source language model by WasamiKirua. Features: 24b LLM, VRAM: 47.3GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.16.

4bit Autotrain compatible Conversational Endpoints compatible Instruct It Mistral Quantized Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth

Model Card on HF 🤗: https://huggingface.co/WasamiKirua/Mistral-Small-24B-new-params-16bit

Mistral Small 24B New Params 16bit Parameters and Internals

LLM Name	Mistral Small 24B New Params 16bit
Repository 🤗	https://huggingface.co/WasamiKirua/Mistral-Small-24B-new-params-16bit
Base Model(s)	unsloth/mistral-small-24b-instruct-2501-unsloth-bnb-4bit unsloth/mistral-small-24b-instruct-2501-unsloth-bnb-4bit
Model Size	24b
Required VRAM	47.3 GB
Updated	2025-04-11
Maintainer	WasamiKirua
Model Type	mistral
Instruction-Based	Yes
Model Files	4.8 GB: 1-of-10 4.8 GB: 2-of-10 4.8 GB: 3-of-10 4.9 GB: 4-of-10 4.8 GB: 5-of-10 4.8 GB: 6-of-10 4.9 GB: 7-of-10 4.8 GB: 8-of-10 4.8 GB: 9-of-10 3.9 GB: 10-of-10
Supported Languages	it
Quantization Type	4bit
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.48.3
Tokenizer Class	LlamaTokenizer
Padding Token	<pad>
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the Mistral Small 24B New Params 16bit 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 Small 24B New Params 16bit

Best Alternatives	Context / RAM	Downloads	Likes
Devstral Small 2507 Bnb 4bit	128K / 14.2 GB	398	1
...al Small 2507 Unsloth Bnb 4bit	128K / 15 GB	128	5
...al Small 2506 Unsloth Bnb 4bit	40K / 15 GB	109	4
Magistral Small 2506 Bnb 4bit	40K / 14.2 GB	38	1
...l Small 24B Instruct 2501 4bit	32K / 13.3 GB	1344	14
Not So Small Alpaca 24B	32K / 47.3 GB	14	0
Napoleon 24B V0.0	32K / 47.3 GB	18	0
...all 24B Instruct 2501 Bnb 4bit	32K / 14.2 GB	4725	3
...Instruct 2501 Unsloth Bnb 4bit	32K / 15 GB	2955	19
...b With Nemotron Converted Vllm	32K / 47.3 GB	38	0

Note: green Score (e.g. "73.2") means that the model is better than WasamiKirua/Mistral-Small-24B-new-params-16bit.