Devstral-2-123B-Instruct-2512
Devstral is an agentic LLM for software engineering tasks. Devstral 2 excels at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench.
Params
125.0 B
Context
262,144
Downloads 30d
5 K
Likes
356
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)5 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 | 256.5 GB | 301.4 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 256.5 GB | 882.8 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/devstral-2-123b-instruct-2512
{
"hf_id": "mistralai/Devstral-2-123B-Instruct-2512",
"params_b": 125.03,
"context_length": 262144,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 5315,
"vram_estimates": [
{ "quant": "f8_e4m3", "gb": 301.4 }
],
"updated_at": "2026-10-19T06:00:13Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.40
input / 1M
$2.00
output / 1M
$0.04
cached input / 1M
$2.40
1M in + 1M out
- Context window
- 262,144 tokens
- Max output
- 209,715 tokens
- Providers
- 1
- Cheapest provider
- Mistral · $0.40 / $2.00
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 8.6 / 31.3 / 2.3
✓ Tool calling
✗ Reasoning
✓ Structured outputs
✗ Image input
✓ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- Ministral3ForCausalLM
- Parameters
- 125.0 B
- Tensor type
- F8_E4M3
- Context length
- 262,144
- Vocabulary
- 131,072
- Layers / heads
- 88 / 96
- Licence
- other
- First seen on the Hub
- 2025-11-28
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model