Ollama · magistral

<img src="/assets/library/mistral-small3.1/88f81c26-7028-4f08-b906-92b873d5536e" width="120" /> Magistral is the first reasoning model by Mistral AI, excelling in domain-specific, transparent, and mu…

ollama/magistral

<img src="/assets/library/mistral-small3.1/88f81c26-7028-4f08-b906-92b873d5536e" width="120" />

Magistral is the first reasoning model by Mistral AI, excelling in domain-specific, transparent, and multilingual reasoning.

![magistral small comparison to medium](/assets/library/magistral/c57cd779-0588-4d74-9f48-89ba50f7a565)

![magistral small](/assets/library/magistral/fe972176-2881-42bc-bbd8-90a079188aa9)

### Key features

- **Reasoning:** Capable of long chains of reasoning traces before providing an answer. - **Multilingual:** Supports dozens of languages, including English, French, German, Greek, Hindi, Indonesian, Italian, Japanese, Korean, Malay, Nepali, Polish, Portuguese, Romanian, Russian, Serbian, Spanish, Swedish, Turkish, Ukrainian, Vietnamese, Arabic, Bengali, Chinese, and Farsi. - **Apache 2.0 License:** Open license allowing usage and modification for both commercial and non-commercial purposes. - **Context Window:** A 128k context window, **but** performance might degrade past **40k**. Hence we recommend setting the maximum model length to 40k.

Magistral is ideal for general purpose use requiring longer thought processing and better accuracy than with non-reasoning LLMs. From legal research and financial forecasting to software development and creative storytelling — this model solves multi-step challenges where transparency and precision are critical.

#### Business strategy and operations.

Building on our flagship [models](https://mistral.ai/models), Magistral is designed for research, strategic planning, operational optimization, and data-driven decision making — whether executing risk assessment and modelling with multiple factors, or calculating optimal delivery windows under constraints.

#### Regulated industries and sectors.

Legal, finance, healthcare, and government professionals get traceable reasoning that meets compliance requirements. Every conclusion can be traced back through its logical steps, providing auditability for high-stakes environments with domain-specialized AI.

#### Systems, software, and data engineering.

Magistral enhances coding and development use cases: compared to non-reasoning models, it significantly improves project planning, backend architecture, frontend design, and data engineering through sequenced, multi-step actions involving external tools or API.

#### Content and communication.

Our early tests indicated that Magistral is an excellent creative companion. We highly recommend it for creative writing and storytelling, with the model capable of producing coherent or — if needed — delightfully eccentric copy.

### Reference

- [Magistral paper](https://mistral.ai/static/research/magistral.pdf) - [Blog post](https://mistral.ai/news/magistral)

Specifications & capabilities

Published model ID
magistral

Deployments & artifacts

1–5 / 5

ollama

source id
ollama
execution mode
local
parameter size
23.6B
parameter count
23600000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
39000
context window is approximate
true
artifact size bytes
14333920644
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
23.6B
parameter count
23600000000
parameter count is approximate
true
quantization level
F16
context window
39000
context window is approximate
true
artifact size bytes
47153530180
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
23.6B
parameter count
23600000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
39000
context window is approximate
true
artifact size bytes
14333920644
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
23.6B
parameter count
23600000000
parameter count is approximate
true
quantization level
Q8_0
context window
39000
context window is approximate
true
artifact size bytes
25054791044
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
23.6B
parameter count
23600000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
39000
context window is approximate
true
artifact size bytes
14333920644
updated at
2026-11-16T08:10:06.079865+00:00

Original sources

1–2 / 2

Ollama · Model page ↗

Ollama · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace