Phi 3.5 Moe Instruct
Microsoft's Phi-3.5 Moe Instruct is a lightweight, open-source chat model designed for memory- and compute-constrained environments and latency-sensitive scenarios. It is built with a focus on high-quality, reasoning-dense data and excels at tasks involving code, math, and logic.
Input
Output
Context
131K
Max Output
4K
Parameters
41.9B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Resources & Links
Estimated GPU requirements for Phi 3.5 Moe Instruct
Estimates based on INT8 quantization at up to 32K context. A count above one assumes tensor parallelism across the cards. Actual requirements vary by framework and configuration.
More models by Microsoft
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about Phi 3.5 Moe Instruct
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
Phi 3.5 Moe Instruct advertises a context window of 131,072 tokens, with a maximum output of 4,096 tokens in a single response. The figure is the creator's published maximum; a given host may serve less, and the gateway routes on what each host actually serves.
Yes. Phi 3.5 Moe Instruct is an open-weight model released under the MIT license, so the weights can be downloaded and self-hosted within that license's terms.
Phi 3.5 Moe Instruct accepts Text and produces Text. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
No published benchmark result for Phi 3.5 Moe Instruct is in the catalog yet, so the model is shown as unmeasured. It is not ranked or estimated; the router treats it as unknown for every task until a suite measures it.
Not on the managed pool today; Phi 3.5 Moe Instruct is listed for reference and comparison. Connect your own provider key or endpoint that serves it and the gateway runs it on your account, with routing decisions recorded the same way.
About 41.0 GB at INT8 for the weights and a default context, from the catalog's 41.9B parameter count; FP16 needs roughly twice that, and long contexts or many concurrent requests add KV cache on top. The GPU section on this page lists cards that hold it, and the capacity planner sizes it for your context length and traffic.
Fields collected from public registries, host APIs and benchmark publishers, each tagged with its source.
Last updated: Sep 11, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.