Back to leaderboard

phi4:14b

OLLAMA GGUF

phi3 · 14.7B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

qwen/qwen3-8b

LM-STUDIO MLX

qwen3 · 8B · 4bit

Excellent

Mar 5, 2026 · Apple M4 Pro

Global Score
77 vs 89
Hardware Fit
74 vs 95
Quality Score
78 vs 87

Hardware

phi4:14b qwen/qwen3-8b
MachineNVIDIA NVIDIA_DGX_SparkMac mini
CPUCortex-X925Apple M4 Pro
Cores2014
RAM122 GB64 GB
GPUDevice 2e12Apple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 15.7.4
Archarm64arm64
Power Modeperformancebalanced

Performance

phi4:14b qwen/qwen3-8b
Tokens/sec22.933.4
First chunk198 ms257 ms
TTFT198 ms257 ms
Load time10.3 sN/A
Memory usage14.7 GB4.3 GB
Memory %12%7%

HW Fit Score Breakdown

phi4:14b

Speed
24/50
TTFT
20/20
Memory
30/30

qwen/qwen3-8b

Speed
45/50
TTFT
20/20
Memory
30/30

Quality

phi4:14b

Reasoning
18/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen/qwen3-8b

Reasoning
19/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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