Phi 3.5 MoE instruct

Name: Phi 3.5 MoE instruct
Author: Microsoft

by MicrosoftPhi 3.5

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released August 2024131K context≈ 98,304 words42.0B params

Phi 3.5 MoE punches well above its active parameter count by routing each token through a small subset of its 42B parameters — meaning it runs faster than its total size suggests. It handles instruction-following, reasoning, and coding tasks with notable precision for a model of its compute footprint. The trade-off is that MoE architectures require more memory to load than dense models of equivalent active parameters.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Long Context

Strong

Instruction Following

Phi 3.5 MoE instruct

by MicrosoftPhi 3.5

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released August 2024131K context≈ 98,304 words42.0B params

Phi 3.5 MoE punches well above its active parameter count by routing each token through a small subset of its 42B parameters — meaning it runs faster than its total size suggests. It handles instruction-following, reasoning, and coding tasks with notable precision for a model of its compute footprint. The trade-off is that MoE architectures require more memory to load than dense models of equivalent active parameters.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Long Context

Strong

Instruction Following

Glossary

Active Parameter CountThe number of model parameters that are actually used during inference for a given input, as opposed to the total parameters available.Active ParametersThe subset of a model's total parameters that are actually used during inference for each input, as opposed to all parameters being used every time.Instruction-FollowingThe ability of a model to understand and execute specific tasks or commands given in natural language prompts.Parameter CountThe total number of adjustable weights in a model; more parameters generally mean more capacity to learn, but also require more computing power.ParametersThe learned numerical values in a model — more parameters generally means more capacity but higher compute cost.PrecisionThe level of numerical detail a model uses to represent its internal values; higher precision means more accurate calculations but requires more memory.ReasoningThe model's ability to work through multi-step logical problems and provide justified answers rather than just pattern-matching.RoutingThe mechanism that decides which specialized sub-networks (experts) should process each input in a mixture-of-experts model.TokenA small unit of text (a word, subword, or punctuation mark) that a language model breaks input into for processing.

Phi 3.5 MoE instruct

Capabilities

Phi 3.5 MoE instruct

Capabilities

Benchmark Scores

Use Case Fit

Glossary