phi-1_5
LM-STUDIO GGUFphi2 · Q8_0
Mar 6, 2026 · Intel Core™ i5-5300U
gemma-4-31b-it-mlx
LM-STUDIO MLXgemma4 · 31B · 8bit
Aug 19, 2026 · Apple M4 Max
Global Score
28 vs 85
Hardware Fit
66 vs 64
Quality Score
11 vs 94
Hardware
phi-1_5 gemma-4-31b-it-mlx
MachineLENOVO 20BUS00700MacBook Pro
CPUIntel Core™ i5-5300UApple M4 Max
Cores416
RAM16 GB128 GB
GPUIntel(R) HD Graphics 5500Apple M4 Max
OSMicrosoft Windows 10 Professionnel 10.0.19045macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced
Performance
phi-1_5 gemma-4-31b-it-mlx
Tokens/sec6.913.6
First chunk3040 ms16 ms
TTFT3.0 s558 ms
Load timeN/A12.3 s
Memory usage1.4 GB0.0 GB
Memory %9%0%
HW Fit Score Breakdown
phi-1_5
Speed
24/50
TTFT
16/20
Memory
26/30
gemma-4-31b-it-mlx
Speed
14/50
TTFT
20/20
Memory
30/30
Quality
phi-1_5
Reasoning
2/20
Coding
2/20
Instruction
3/20
Structured
0/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
gemma-4-31b-it-mlx
Reasoning
19/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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