- Source
- Model registry API
- Verified
- 19 Sep 2026
- Confidence
- High
01What this is
- Author
- mistralai
- Family
- Devstral 2
- Task
- text-generation
- Hugging Face
- mistralai/Devstral-2-123B-Instruct-2512
- OpenRouter
- mistralai/devstral-2512
- Also known as
- Devstral 2, devstral-2-123b, devstral
02Registry facts
- LicenceFACT
other
- FreshRetrieved 19 Sep 2026
- ParametersFACT
125.0B
- FreshRetrieved 19 Sep 2026
- Context lengthFACT
not returned by the registry
- Evidence not verified
- Downloads (30 days)FACT
15,329
- FreshRetrieved 19 Sep 2026
- LikesFACT
340
- FreshRetrieved 19 Sep 2026
- GatedFACT
no
- FreshRetrieved 19 Sep 2026
Model
- downloadsFACT
15329
- Verification may be outdatedRetrieved 19 Sep 2026
- gatedFACT
false
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · MistralFACT
262144
- Verification may be outdatedRetrieved 19 Sep 2026
- likesFACT
340
- Verification may be outdatedRetrieved 19 Sep 2026
- model licenseFACT
other
- Verification may be outdatedRetrieved 19 Sep 2026
- parameter countFACT
125025989840
- Verification may be outdatedRetrieved 19 Sep 2026
Pricing
- hosted price completion per m · MistralFACT
2.0000
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · MistralFACT
0.4000
- AgeingRetrieved 19 Sep 2026
Other
- available on platform · vendorFACT
vendor
Evidence not verified — the quoted phrase was not found in the fetched document.
- Evidence not verified
- available on platform · awsFACT
aws
The source document changed after this was recorded; it is queued for re-checking.
- Verification may be outdatedRetrieved 19 Sep 2026
- last modifiedFACT
2026-07-15T12:19:49.000Z
- Verification may be outdatedRetrieved 19 Sep 2026
- libraryFACT
vllm
- AgeingRetrieved 19 Sep 2026
03VRAM by quantisation
Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: 125.0B parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).
| Quantisation | Weights | Total |
|---|---|---|
| bf16bf16 is two bytes per weight, the same arithmetic as fp16. | 250.05 GB | 304.85 GB |
| fp8 | 125.03 GB | 161.07 GB |
| int4 | 62.51 GB | 89.18 GB |
What this estimate assumes
- Weights: 125.0B parameters × 2 bytes per parameter (fp16) = 250.05 GB.
- No model configuration was supplied, so the KV cache uses the size heuristic for this band: 0.459 MB per token, from extrapolated above 90B — no configuration was fetched for this band.
- KV cache: 0.459 MB per token × 8,192 tokens of context × 4 concurrent requests = 15.03 GB, sized for every user holding a full context at once.
- Overhead: 15% of weights plus KV cache for the runtime, activations and memory fragmentation = 39.76 GB.
- GB means 10⁹ bytes, matching how GPU memory is advertised.
- KV cache held at fp16 (2 bytes per element); quantising weights does not by itself quantise the cache.
- Peak figure, not average: prefix caching and paged attention usually keep real usage lower, while speculative decoding, CUDA graphs and a second resident model push it higher.
- "Concurrent" counts requests generated at the same instant, not people: 4 simultaneous requests is the worst case this estimate is built on — measure yours before buying.
04Hardware profiles
No hardware profile was sized for this answer.
05Hosted providers
- Prompt (per million tokens, USD)FACT
0.39999999999999997
Source: openrouter
- FreshRetrieved 19 Sep 2026
- Completion (per million tokens, USD)FACT
2
- FreshRetrieved 19 Sep 2026
| Provider | Context |
|---|---|
| Mistral | 262,144 |
06Deployment stacks
No published deployment stack names this model yet.
07Evidence
- 01Tier 2official vendor legal documentationVendor legal and technical documentation
Models at a glance - Amazon Bedrock
https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards.html
AgeingRetrieved 19 Sep 2026sha256:4c3b2b5762261 record
- 02–04Tier 4official repository / model cardOpenRouter
OpenRouter endpoints — mistralai/devstral-2512
https://openrouter.ai/api/v1/models/mistralai/devstral-2512/endpoints
AgeingRetrieved 19 Sep 2026sha256:2ef4ec50068c3 records · ·
- 05–11Tier 4official repository / model cardHugging Face Hub
Hugging Face model card data — mistralai/Devstral-2-123B-Instruct-2512
https://huggingface.co/api/models/mistralai/Devstral-2-123B-Instruct-2512
AgeingRetrieved 19 Sep 2026sha256:a1f1338707b07 records · · · · · ·
Improve this page
Sign in to contribute
From the field
0 deployments · 0 questions
Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.