lmstudio-community/gemma-4-e4b-it
LM-STUDIO GGUFgemma4 · Q4_K_M
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
76 vs 75
Hardware Fit
67 vs 79
Quality Score
80 vs 73
Hardware
lmstudio-community… phi4:14b
MachineDocker ContainerMacBook Air
CPUIntel Gen Intel® Core™ i9-11900HApple M4
Cores1610
RAM15 GB32 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M4
OSUbuntu 26.04 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
lmstudio-community… phi4:14b
Tokens/sec10.811.0
First chunk44 msN/A
TTFT2.0 s532 ms
Load time10.9 s0.7 s
Memory usage0.0 GB13.4 GB
Memory %0%42%
HW Fit Score Breakdown
lmstudio-community/gemm…
Speed
20/50
TTFT
17/20
Memory
30/30
phi4:14b
Speed
19/50
TTFT
30/20
Memory
30/30
Quality
lmstudio-community/gemm…
Reasoning
14/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
phi4:14b
Reasoning
15/20
Coding
18/20
Instruction
10/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest