mistral-ai/mistral/ministral-3-3b-instruct-2512-onnx
Source details
Source revision: 83a2abb7373ad8edafd0e01c0e13e72b9576e9f39c2c946a5a447460598299f7
Mistral AI · Text
Mistral offers distinct Large, Medium, Small, Ministral, Devstral and multimodal branches with materially different deployment profiles.
Mistral is an official Mistral AI model family represented here through independently verified release, checkpoint, license, runtime and hardware evidence. Mistral offers distinct Large, Medium, Small, Ministral, Devstral and multimodal branches with materially different deployment profiles. Current public releases are grouped by the Generalist Large, Generalist Medium, Generalist Small, Ministral, Devstral, Codestral, Multimodal tracks so sibling sizes and specialist branches are not presented as false chronological generations.
FusionPointAI currently tracks 17 certified public Mistral releases. The catalogue preserves release dates and evaluates Current, Recent, Previous and Legacy status within each model track rather than by database insertion order.
The verified public range spans 3.85B to 675B total parameters and context windows up to 1,048,576 tokens. Each release states whether it is dense or mixture-of-experts and records active parameters separately when the official source publishes them.
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
128.0B parameters · 262,144 context
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
The manufacturer has not published this information. parameters · N/A / Not directly comparable context
3.8B parameters · 262,144 context
8.9B parameters · 262,144 context
14.0B parameters · 262,144 context
Choose a specific Mistral release and certified checkpoint before sizing hardware. FusionPointAI rejects unknown runtime configurations, calculates resident memory from total model weights, then distinguishes globally compatible GPUs from currently rentable inventory.
Validate the exact checkpoint license, runtime version, precision kernel, context length, concurrency and multi-GPU topology. Active MoE parameters affect compute, but resident model memory continues to use total stored weights.
Licenses are certified per release, not inferred from the provider. Review the release page before commercial deployment because terms can differ between generations and variants.
Commercial-use status is a source-backed catalogue classification, not legal advice. Follow the linked official license and attribution requirements.
Source revision: 83a2abb7373ad8edafd0e01c0e13e72b9576e9f39c2c946a5a447460598299f7
Source revision: 59a570dc699adbf15bea3edcd1c2b43bda5eddd8bf1e662e3d39f7dc0141fc36
Source revision: 965dfb604113b53c14bc21044d20f5872b48944594910e4c0acba3be4611201d
Source revision: 66036512d4b7c817a4b90d97717251fe8c65dcd3b056fbe634ced2b489aac064
Source revision: 217105cc61bd6fcc129c9dc8e0cc47907924d81d53a0148d5d1c4f2b52f8d509
Source revision: 14eda27e6d23fcf912acd018f1384d7dee974f329d2becce93544a5dbd9a38f3
Source revision: bd6dc6b9d18a72d3a09e68492438a99b4c0bc8ced688686458f2e9e2116d5a87
Source revision: 37909a0153738d7a6b9e5172ae822191318b7a5f040a84c8346965a01c32d5c4
Source revision: 3c894e9887e10a0e048cf6875d183a2387181ad333678430fdd8e5ab537b889c
Source revision: e494b5f811f74e408fac66405e32dce9aea5a44512315b26b4aaeb76a7529fd2
Source revision: 460b20232cd5dbd2dc6244a3a1b97b586429cac24c9298216721c2fb9361bfe8
Source revision: 14da8cf90107826392038e085efee53f886d7371dde31dc9ac6ca8b6868c6cc2
Source revision: 2db7feae217eadd1ceeb051f5db5287b975d5786155df54bba7b44137234c275
Source revision: 7e08bd7310f56d26bdf220ff6c7a3ae22e176e1621da4988950eb2f605dc3068
Source revision: 17e746573df3af5648277fa5ccf3abaa705c7332b91b696e8a9e8347ce21cf2e
Source revision: f93b5938d9049ceb8ead7ec88694ec6cc2d06a899349fa1eeb19296b7426b0ff
Source revision: 8420c26c95662760e5c341735be4944301859d72c8c05ff91186c251331b7ad2
Current releases are Mistral Medium 3.5 128B, Mistral Small 4 119B A6B, Devstral Small 2 24B, Mistral Large 3 675B Instruct 2512, Ministral 3 14B Instruct 2512, Ministral 3 8B Instruct 2512, Ministral 3 3B Instruct 2512, Devstral 2 123B Instruct 2512, Mistral-Medium-3.5-128B, Ministral-3-14B-Instruct-2512, Ministral-3-3B-Instruct-2512, evaluated within their respective tracks.
Only releases with a verified official checkpoint and supported runtime configuration are presented as deployable.
GPU selection depends on the exact variant, checkpoint precision, context length and concurrency; use the release hardware recommendations rather than the family name alone.
Last verified: 2026-09-03