Back to leaderboard

phi4-mini:latest

OLLAMA GGUF

phi3 · 3.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

qwen3.8-27b-mlx

LM-STUDIO UNKNOWN

27B

Good

Aug 17, 2026 · Apple M5 Max

Global Score
74 vs 66
Hardware Fit
98 vs 91
Quality Score
63 vs 55

Hardware

phi4-mini:latest qwen3.8-27b-mlx
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M5 Max
Cores618
RAM7 GB64 GB
GPUIntegrated / UnknownApple M5 Max
OSUbuntu 22.04.5 LTSmacOS 27.0
Archarm64arm64
Power Modebalancedbalanced

Performance

phi4-mini:latest qwen3.8-27b-mlx
Tokens/sec18.433.2
First chunk1078 ms7 ms
TTFT1.1 s311 ms
Load time6.4 sN/A
Memory usage2.9 GB0.5 GB
Memory %39%1%

HW Fit Score Breakdown

phi4-mini:latest

Speed
50/50
TTFT
20/20
Memory
28/30

qwen3.8-27b-mlx

Speed
41/50
TTFT
20/20
Memory
30/30

Quality

phi4-mini:latest

Reasoning
13/20
Coding
11/20
Instruction
14/20
Structured
11/15
Math
5/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Strong

qwen3.8-27b-mlx

Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest