Back to leaderboard

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

starling-lm:7b

OLLAMA GGUF

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
71 vs 63
Hardware Fit
88 vs 97
Quality Score
63 vs 49

Hardware

qwen3.5-4b-mlx 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

qwen3.5-4b-mlx starling-lm:7b
Tokens/sec23.123.7
First chunk3279 msN/A
TTFT3.3 s234 ms
Load timeN/A0.4 s
Memory usage2.9 GB5.3 GB
Memory %9%17%

HW Fit Score Breakdown

qwen3.5-4b-mlx

Speed
45/50
TTFT
13/20
Memory
30/30

starling-lm:7b

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

Quality

qwen3.5-4b-mlx

Reasoning
15/20
Coding
16/20
Instruction
6/20
Structured
6/15
Math
11/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Weak 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
View qwen3.5-4b-mlx details | View starling-lm:7b 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