what/llm/can/i/run
models/microsoft-phi-3-mini-128k-instruct

ΦPhi 3 Mini 128k

Sources arena, livebench · Confidence B
params
dense
bench sources
2
mid conf
context
max tokens
license
MIT
permissive

Model meta

canonical
microsoft/Phi-3-mini-128k-instruct
parameters
organization
Microsoft
license
MIT
context
downloads

Benchmark breakdown

LiveBench
instruction following54.8
coding16.8
language7.5
overall26.4

Hardware fit matrix

by gpu tierQ2_K
Q4_K_M
Q5_K_M
Q6_K
Q8_0
FP16
G8 GB tier
rtx 3050 · 4060
G12 GB tier
rtx 3060 · 4070
G16 GB tier
rtx 4080 · 4060 ti 16g
G24 GB tier
rtx 3090 · 4090
G32 GB tier
rtx 5090 · m3 max
G48 GB tier
a6000 · m3 max 64
G80 GB tier
h100 · m3 ultra 128
full fit · production speed tight fit · usabledoesn't fit
Get personalized ranking
Tell us your machine — we'll tell you if this is actually your best pick, or what's better.
Rank for my hardware