Mistral-Small-4-119B-2603
Mistral Small 4 is a powerful hybrid model capable of acting as both a general instruction model and a reasoning model. It unifies the capabilities of three different model families—Instruct, Reasoning (previously called Magistral), and Devstral—into a single, unified model.
Params
119.4 B
Context
—
Downloads 30d
69 K
Likes
457
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)69 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f8_e4m3 | 241.9 GB | 284.4 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/mistral-small-4-119b-2603
{
"hf_id": "mistralai/Mistral-Small-4-119B-2603",
"params_b": 119.40,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 68887,
"vram_estimates": [
{ "quant": "f8_e4m3", "gb": 284.4 }
],
"updated_at": "2026-10-19T06:00:08Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.15
input / 1M
$0.60
output / 1M
$0.015
cached input / 1M
$0.75
1M in + 1M out
:batch variant
$0.075 in · $0.30 out
- Context window
- 262,144 tokens
- Max output
- 209,715 tokens
- Providers
- 1
- Cheapest provider
- Mistral · $0.15 / $0.60
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 11.3 / 26.6 / 0.8
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✓ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- Mistral3ForConditionalGeneration
- Parameters
- 119.4 B
- Tensor type
- F8_E4M3
- Licence
- apache-2.0
- First seen on the Hub
- 2026-01-23
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model