Phi-3.5-MoE-instruct

Microsoft · released 2024-08-01 · MIT license

Phi-3.5-MoE-instruct is Microsoft's Aug-2024 MoE (16x3.8B, 6.6B active, MIT, 128K) and the strongest Phi-3.5 model, rivaling larger models on reasoning and long-context retrieval (MMLU-Pro 54.3, RULER 87.1).

Key specs

TypeLocal open-weight
Parameters41.87B total
Architecturephimoe
Context window131K tokens
Knowledge cutoff2023-10-01
Modalitiestext
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond
SWE-bench Verified
AIME
MMLU-Pro54.3%
BFCL v3 (tool use)
Composite score5.95
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M25.8 GB24.3 GB131K

Strengths & weaknesses

Strengths: Strong reasoning/knowledge for 6.6B active (MMLU 78.9); Best-in-class long-context retrieval (RULER 87.1), 128K; MIT MoE (16x3.8B)

Weaknesses: Higher memory footprint than dense small models; Limited factual recall typical of Phi family