Phi 3.5 Mini Instruct phi-3.5-mini-instruct

microsoft · microsoft

unranked — no quality signals yet

params
3.8B
arch
dense
license
mit open weights
released
Aug 2024
downloads/30d
327.0k

# architecture

attn shared MHA ×32 feed-forward (dense) every parameter, every token out ×32 layers 3.8B — no routing
layers
32
d_model
3072
heads
32q / 32kv
head dim
96
vocab
32064
family
phi3

signal path of one layer, generated from the registry's structured fields — dimension lines quote the model's real numbers; an MoE trace forks at the router, a dense trace runs straight through. Geometry fields come from the repo's config.json.

# trend

collecting history — trends appear after a few daily runs.

# benchmarks

benchmarkscoresourcedate
Arc-c 0.8 / 1 LLM Stats
Arena-hard 0.4 / 1 LLM Stats
Big-bench-hard 0.7 / 1 LLM Stats
Boolq 0.8 / 1 LLM Stats

# where to run

providerquantctx$/M in$/M out$/M cacheprice srctpsuptime
Azure 125k $0.13$0.52 via litellm

sorted by blended price ((3·input + output) / 4 per 1M) · ✓ = the provider's own catalog confirms the offer · "via …" prices are what the aggregator routing the offer charges, not the provider's own list price

source aliases
llmstats
phi-3.5-mini-instruct