Ollama · mistral-small

<img src="https://ollama.com/assets/library/mistral-small/87657512-b656-4c53-a8bd-64f0591d6fa9" width="200"/> Mistral Small 3 sets a new benchmark in the "small" Large Language Models category below …

ollama/mistral-small

<img src="https://ollama.com/assets/library/mistral-small/87657512-b656-4c53-a8bd-64f0591d6fa9" width="200"/>

Mistral Small 3 sets a new benchmark in the "small" Large Language Models category below 70B, boasting 24B parameters and achieving state-of-the-art capabilities comparable to larger models.

Mistral Small can be deployed locally and is exceptionally "knowledge-dense", fitting in a single RTX 4090 or a 32GB RAM MacBook once quantized. Perfect for:

- Fast response conversational agents. - Low latency function calling. - Subject matter experts via fine-tuning. - Local inference for hobbyists and organizations handling sensitive data.

### Key Features - **Multilingual:** Supports dozens of languages, including English, French, German, Spanish, Italian, Chinese, Japanese, Korean, Portuguese, Dutch, and Polish. - **Agent-Centric:** Offers best-in-class agentic capabilities with native function calling and JSON outputting. - **Advanced Reasoning:** State-of-the-art conversational and reasoning capabilities. - **Apache 2.0 License:** Open license allowing usage and modification for both commercial and non-commercial purposes. - **Context Window:** A 32k context window. - **System Prompt:** Maintains strong adherence and support for system prompts. - **Tokenizer:** Utilizes a Tekken tokenizer with a 131k vocabulary size.

### Human Evaluations ![Human ratings](/assets/library/mistral-small/90f227bd-9751-4fe9-aa23-4d5d89b9d0c6)

We conducted side by side evaluations with an external third-party vendor, on a set of over 1k proprietary coding and generalist prompts. Evaluators were tasked with selecting their preferred model response from anonymized generations produced by Mistral Small 3 vs another model. We are aware that in some cases the benchmarks on human judgement starkly differ from publicly available benchmarks, but have taken extra caution in verifying a fair evaluation. We are confident that the above benchmarks are valid.

### Instruct performance Our instruction tuned model performs competitively with open weight models three times its size and with proprietary GPT4o-mini model across Code, Math, General knowledge and Instruction following benchmarks.

![instruct performance](/assets/library/mistral-small/d27f75e4-0dae-4721-bade-2999a1dd4a7b) ![instruct performance](/assets/library/mistral-small/e677ae9e-edfa-47f9-a35c-b1eb9dfb51c8)

![instruct performance](/assets/library/mistral-small/4545bb49-d87f-4731-bfdb-e191dc2c2a9a)

Performance accuracy on all benchmarks were obtained through the same internal evaluation pipeline - as such, numbers may vary slightly from previously reported performance (Qwen2.5-32B-Instruct, Llama-3.3-70B-Instruct, Gemma-2-27B-IT). Judge based evals such as Wildbench, Arena hard and MTBench were based on gpt-4o-2024-05-13. Customers are evaluating Mistral Small 3 across multiple industries, including:

- Financial services customers for fraud detection - Healthcare providers for customer triaging - Robotics, automotive, and manufacturing companies for on-device command and control - Horizontal use cases across customers include virtual customer service, and sentiment and feedback analysis.

Specifications & capabilities

Published model ID
mistral-small

Deployments & artifacts

1–20 / 21

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q4_0
context window
128000
context window is approximate
true
artifact size bytes
12569171655
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
F16
context window
128000
context window is approximate
true
artifact size bytes
44496737991
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q2_K
context window
128000
context window is approximate
true
artifact size bytes
8272107207
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q3_K_L
context window
128000
context window is approximate
true
artifact size bytes
11730441927
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q3_K_M
context window
128000
context window is approximate
true
artifact size bytes
10756839111
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q3_K_S
context window
128000
context window is approximate
true
artifact size bytes
9641285319
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q4_0
context window
128000
context window is approximate
true
artifact size bytes
12569171655
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q4_1
context window
128000
context window is approximate
true
artifact size bytes
13947000519
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q4_K_M
context window
128000
context window is approximate
true
artifact size bytes
13341251271
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q4_K_S
context window
128000
context window is approximate
true
artifact size bytes
12660397767
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q5_0
context window
128000
context window is approximate
true
artifact size bytes
15324829383
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q5_1
context window
128000
context window is approximate
true
artifact size bytes
16702658247
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q5_K_M
context window
128000
context window is approximate
true
artifact size bytes
15722567367
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q5_K_S
context window
128000
context window is approximate
true
artifact size bytes
15324829383
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q6_K
context window
128000
context window is approximate
true
artifact size bytes
18252715719
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
local
parameter size
22.2B
parameter count
22200000000
parameter count is approximate
true
quantization level
Q8_0
context window
128000
context window is approximate
true
artifact size bytes
23640561351
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
32000
context window is approximate
true
artifact size bytes
14333921100
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
32000
context window is approximate
true
artifact size bytes
47153530700
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
32000
context window is approximate
true
artifact size bytes
14333921100
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
32000
context window is approximate
true
artifact size bytes
25054791500
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