How much VRAM does Magistral Small 24B need?

Magistral Small 24B requires approximately 0.0 GB VRAM at Q4_K_M quantization with 1K context and 10% overhead. At Q8_0 it needs ~0.0 GB, and at FP16 ~0.0 GB. Use the PCPARTGUIDE VRAM Calculator for exact requirements at any context length and overhead setting.

Can I run Magistral Small 24B on a consumer GPU?

Yes, Magistral Small 24B can run on consumer GPUs. At Q4_K_M quantization with moderate context length, it fits on a 24 GB GPU. For best performance, use a 24 GB or larger GPU with at least 8 GB VRAM for reasonable context lengths.

What is Magistral Small 24B's context window?

Magistral Small 24B supports a maximum context window of 131,072 tokens. The default context is 4,096 tokens. Larger contexts require proportionally more VRAM for the KV cache — use the VRAM Calculator to estimate exact requirements at your target context length.

What quantization level should I use for Magistral Small 24B?

For Magistral Small 24B, start with Q4_K_M (~0.0 GB) if VRAM-limited. Q8_0 offers better quality at ~2× the VRAM. If you have enough VRAM, Q6_K (~1.5× Q4 VRAM) provides a good balance. For models this large, Q3_K_M may be necessary to fit on consumer hardware.

How does Magistral Small 24B compare to similar models?

Magistral Small 24B is a 24.0B Dense model from the Mistral family. Browse other Mistral models on the PCPARTGUIDE directory for comparable alternatives with different parameter counts and VRAM requirements. Use the Model Transparency scores to assess documentation quality and reproducibility.

MistralDenseApache 2.0

Magistral Small 24B

Magistral Small 24B is a dense transformer language model from the Mistral family, containing 24B parameters across 56 layers. It supports up to 131K tokens of context with a hidden dimension of 6144 and 8 KV heads for efficient grouped-que…

24.0B

Parameters

128K

Max Context

Dense

Architecture

—

Released

Text

Modality

About Magistral Small 24B

Reasoning

Technical Specifications

Total Parameters24.0B

ArchitectureDense

Attention TypeGQA (Grouped Query Attention)

Hidden Dimensiond = 6,144

Transformer Layers56

Attention Heads32

KV Headsn_kv = 8

Head Dimensiond_head = 128

Activation FunctionSwiGLU

NormalizationRMSNorm

Position EmbeddingRoPE

System Requirements

Estimated VRAM at 10% overhead for different quantization methods and context sizes.

Quantization	1K ctx	128K ctx
Q4_K_M0.50 B/W ~97% of FP16	12.62Consumer GPU	40.41Datacenter GPU
Q8_01.00 B/W ~100% of FP16	25.03Datacenter GPU	52.81Datacenter GPU
F162.00 B/W Reference	49.84Datacenter GPU	77.62Datacenter GPU

Params

675.0B

Layers

Context

256K

41.0B active

Find the right GPU for Magistral Small 24B

Use the interactive VRAM Calculator to see exactly how much memory you need at any quantization level, context length, and overhead setting.

Open VRAM Calculator Best GPU Guide VRAM Guide