Back to leaderboard

qwen2.5-7b-instruct

LM-STUDIO MLX

qwen2 · 7B · 4bit

Excellent

Mar 3, 2026 · Apple M4

starling-lm:7b

OLLAMA GGUF

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
84 vs 63
Hardware Fit
97 vs 97
Quality Score
78 vs 49

Hardware

qwen2.5-7b-instruct starling-lm:7b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen2.5-7b-instruct starling-lm:7b
Tokens/sec24.423.7
First chunk464 msN/A
TTFT464 ms234 ms
Load timeN/A0.4 s
Memory usage4.0 GB5.3 GB
Memory %13%17%

HW Fit Score Breakdown

qwen2.5-7b-instruct

Speed
47/50
TTFT
20/20
Memory
30/30

starling-lm:7b

Speed
37/50
TTFT
30/20
Memory
30/30

Quality

qwen2.5-7b-instruct

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

starling-lm:7b

Reasoning
11/20
Coding
13/20
Instruction
6/20
Structured
3/15
Math
8/15
Multilingual
8/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Adequate 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