Microsoft's Phi 3.5 MoE Instruct is an open-source chat model that takes text and returns text. It is a mixture-of-experts model designed for general-purpose tasks, with capabilities for calling functions, structured output, and extended reasoning.
Input
Output
Context
131K
Max Output
4K
Parameters
41.9B
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
None the catalog can show from stated facts or measured scores.
| Precision | Weights | One request at 33K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 78.0 GB | 87.9 GB | 1x AMD Instinct MI250X (128 GB) |
| INT8 | 39.0 GB | 46.9 GB | 1x Biren BR100 (64 GB) |
| INT4 | 19.5 GB | 26.4 GB | 1x Tenstorrent Blackhole p150 (32 GB) |
Computed by Inferbase from the 41,873,153,344 parameters in the creator's Hugging Face repository; one request adds its KV cache, activations and framework overhead, with the layer layout estimated from the parameter count.
Public resources
Specification sources
As of Nov 11, 2026.
Answered from the facts on this page, with their sources.
Phi 3.5 MoE Instruct has a context window of 131,072 tokens and a maximum output of 4,096 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. Phi 3.5 MoE Instruct is an open-weight model under the MIT license. You can download and self-host it within the license terms.
Phi 3.5 MoE Instruct has 41,873,153,344 parameters (41.9B), as stated in the creator's Hugging Face repository.
Strengths: Open weights under a permissive license (mit); 131K token context window. Each is computed from the model's stated facts and benchmark results.
Phi 3.5 MoE Instruct accepts Text and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for Phi 3.5 MoE Instruct yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves Phi 3.5 MoE Instruct, and Inferbase runs it on your account with the same routing and logs.
The weights take 78.0 GB at FP16 / BF16, 39.0 GB at INT8, 19.5 GB at INT4, computed from the 41,873,153,344 parameters its creator publishes. Each request adds its KV cache and the framework's overhead. The hardware section shows one request and the smallest GPU that fits; the GPU planner sizes it for your context length and traffic.
Start on the free plan with 5,000 requests a month, no card required.