Back to leaderboard

qwen2.5:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Mar 16, 2026 · Intel Core™ i7-4771

starcoder2:3b

OLLAMA GGUF

starcoder2 · 3B · Q4_0

Not Rec.

Mar 2, 2026 · Apple M4

Global Score
65 vs 39
Hardware Fit
92 vs 100
Quality Score
54 vs 13

Hardware

qwen2.5:1.5b starcoder2:3b
MachineiMacMacBook Air
CPUIntel Core™ i7-4771Apple M4
Cores810
RAM32 GB32 GB
GPUNVIDIA GeForce GTX 780MApple M4
OSmacOS 15.7.3macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

qwen2.5:1.5b starcoder2:3b
Tokens/sec19.649.4
First chunk690 msN/A
TTFT690 ms155 ms
Load time21.4 s0.4 s
Memory usage1.0 GB3.0 GB
Memory %3%9%

HW Fit Score Breakdown

qwen2.5:1.5b

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

starcoder2:3b

Speed
40/50
TTFT
30/20
Memory
30/30

Quality

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

starcoder2:3b

Reasoning
0/20
Coding
2/20
Instruction
5/20
Structured
2/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

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