Mistral AI Launches Mistral-Medium-3.5-128B Model
Mistral AI has launched its new Mistral-Medium-3.5-128B model, a multimodal model featuring 128 billion parameters. The model is designed for advanced applications involving text and image input.
What happened?
Mistral AI has released Mistral-Medium-3.5-128B, a new dense, multimodal model with 128 billion parameters. The model supports text and image input with text output, featuring a context window of 256K tokens. It is optimised for reasoning, coding, long-context tasks, tool Use, agent-based workflows, and multimodal document and image understanding.
Key facts
| Modellnamn | Mistral-Medium-3.5-128B |
|---|---|
| Antal parametrar | 128 miljarder |
| Modelltyp | Multimodal (Text + Bild) |
| Kontextfönster | 256K tokens |
| Rekommenderat RAM för lokal körning | ~64 GB |
| Datum för inferensfix | 1 maj 2026 |
”Mistral releases Mistral-Medium-3.5-128B, their new dense 128B parameter, multimodal, hybrid reasoning model. It supports text and image input, text output, a 256K context window and excels at reasoning, coding, long-context, tool use, agentic workflows, and multimodal doc/image”
”Mistral Medium 3.5 offers highly competitive performance for models 5x its size. Run locally on ~64GB RAM. GGUF: Mistral-Medium-3.5-128B-GGUF”
”May 1, 2026 Update: We worked with Mistral to fix Mistral Medium 3.5 inference affecting some implementations, and released updated GGUFs with the fix (NOT related to Unsloth or our quants). The issue was caused by a YaRN parsing quirk affecting several implementations, including”
Why it matters
The launch of Mistral-Medium-3.5-128B is significant as it offers competitive performance compared to models five times its size, despite requiring approximately 64 GB of RAM for local execution. This could democratise access to advanced AI capabilities for developers with limited resources. The model's versatility makes it applicable across a wide range of AI applications.
Who is affected?
This launch affects developers working with AI models, particularly those focused on multimodal applications and "local-first" strategies. Companies seeking to implement advanced AI solutions with limited hardware stand to benefit from the model's efficiency. Users seeking more capable AI assistants may also be indirectly affected.
What else you should know
On 1 May 2026, an update was implemented to resolve an inference issue in Mistral Medium 3.5 related to a YaRN interpretation discrepancy affecting several implementations. The fix involved changing `mscale_all_dim` from 1 to 0. This correction has now been integrated into Mistral's official repository.
Quick answers about this story
Vad har hänt?
När hände det?
Varför spelar det roll?
Vilka funktioner har modellen?
The link opens in a new window and leads to the publisher's own site.
Källan har spårats automatiskt från utgivaren via Aheadlines signalkedja.
AI-verktyg i artikeln
Topics
Get similar news straight to your inbox
The reader's room
Send in a question or an addition. The newsroom reads everything before it's published and replies when relevant. No AI-generated text – just people.
Sign in to submit a comment or question.
Read the article through your role
- Decide whether this affects strategy over 6–12 months or is just noise.
- Discuss with leadership: do we own the right question or does ownership need to move?
- Ask: what risk are we taking by NOT acting on this this quarter?
Generated angle — not editorial analysis of "Mistral AI Launches Mistral-Medium-3.5-128B Model"