Mistral Small 4
Intelligence benchmarks
Artificial Analysis indexes - compared with the best open and proprietary models
Intelligence
4.3
AA Index
Coding
0.0
AA Index
Agentic
0.5
AA Index
Intelligence Index - Mistral Small 4 vs. the field
Best open-weight models (you can run locally) and leading proprietary models for context.
Coding Index comparison
Agentic Index comparison
Benchmark data from Artificial Analysis · updated 2026-10-31.
Hosted API cost & speed
What it costs to rent this model instead of running it locally
| Metric | Value |
|---|---|
| Input (per 1M tokens) | $0.15 |
| Output (per 1M tokens) | $0.60 |
| Median speed (hosted API) | 173 tok/s |
Median across hosted providers, measured by Artificial Analysis - updated 2026-10-31. Local llama.cpp speed depends on your hardware — see the hardware pages for estimates.
Standard benchmarks
Performance across standard evaluations
| Benchmark | Score |
|---|---|
| GPQA Diamond | 76.9 |
| HLE | 9.9 |
| SciCode | 38.8 |
| IFBench | 48.2 |
| Terminal-Bench | 17.4 |
Source: Artificial Analysis component evals - updated 2026-10-31.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-NVFP4New to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
Mistral Small 4 is a 14.3B-parameter apache-2.0 model from Mistral. It scores 4.3 on the Artificial Analysis Intelligence Index (coding 0). At Q4_K_M it needs roughly 8 GB of VRAM, placing it in the 8–12 GB GPU hardware tier.
Benchmarks
Artificial Analysis Intelligence Index - Mistral Small 4 vs. leading closed models:
| Model | Intelligence | Coding | GPQA |
|---|---|---|---|
| Mistral Small 4 | 4.3 | 0 | 76.9 |
| Gemini 4 Carbon | 59.4 | 50.4 | - |
| Claude Opus 5.5 | 58.4 | 51.7 | - |
| GPT-6 Astra | 56.9 | 49.1 | 96.1 |
| GPT-6.1 Sol | 54.5 | 46.8 | - |
| Claude Sonnet 5.5 | 54.2 | 50.5 | - |
Source: Artificial Analysis (2026-10-31).
Popularity
Mistral Small 4 has 74,401 downloads in the last month on HuggingFace and 11 likes.
Frequently asked
Quick answers to common questions
How much VRAM does Mistral Small 4 need?
Mistral Small 4 with 14.3B parameters needs approximately 8 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is Mistral Small 4 better than other unsloth models?
Mistral Small 4 has 14.3B parameters with 131,072 context - a strong choice for general use.
What license is Mistral Small 4 under?
Mistral Small 4 is released under the apache-2.0 license, making it suitable for most commercial and personal projects.
What hardware runs Mistral Small 4 well?
With 14.3B parameters, Mistral Small 4 requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for Mistral Small 4?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~10 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can Mistral Small 4's context window handle?
Mistral Small 4 supports a 131,072-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.
What models compete with Mistral Small 4?
Mistral Small 4 competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec