Back to leaderboard

phi-3-mini-128k-instruct

LM-STUDIO MLX

phi3 · 4bit

Not Rec.

Mar 4, 2026 · Apple M4

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Mar 16, 2026 · Intel Core™ i7-4771

Global Score
38 vs 65
Hardware Fit
100 vs 92
Quality Score
12 vs 54

Hardware

phi-3-mini-128k-in… qwen2.5:1.5b
MachineMacBook AiriMac
CPUApple M4Intel Core™ i7-4771
Cores108
RAM32 GB32 GB
GPUApple M4NVIDIA GeForce GTX 780M
OSmacOS 26.3macOS 15.7.3
Archarm64x64
Power Modebalancedbalanced

Performance

phi-3-mini-128k-in… qwen2.5:1.5b
Tokens/sec44.019.6
First chunk384 ms690 ms
TTFT385 ms690 ms
Load timeN/A21.4 s
Memory usage2.0 GB1.0 GB
Memory %6%3%

HW Fit Score Breakdown

phi-3-mini-128k-instruct

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

qwen2.5:1.5b

Speed
42/50
TTFT
20/20
Memory
30/30

Quality

phi-3-mini-128k-instruct

Reasoning
3/20
Coding
2/20
Instruction
2/20
Structured
1/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

qwen2.5:1.5b

Reasoning
8/20
Coding
9/20
Instruction
12/20
Structured
13/15
Math
5/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
View phi-3-mini-128k-in… details | View qwen2.5:1.5b details

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