Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

qwen2.5:0.5b

OLLAMA GGUF

qwen2 · 494.03M · Q4_K_M

Marginal

Mar 2, 2026 · Apple M4

Global Score
59 vs 57
Hardware Fit
65 vs 100
Quality Score
57 vs 39

Hardware

qwen3.5-9b-mlx qwen2.5:0.5b
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5-9b-mlx qwen2.5:0.5b
Tokens/sec14.3165.0
First chunk24 msN/A
TTFT13.4 s81 ms
Load time13.3 s0.5 s
Memory usage2.5 GB1.7 GB
Memory %10%5%

HW Fit Score Breakdown

qwen3.5-9b-mlx

Speed
32/50
TTFT
3/20
Memory
30/30

qwen2.5:0.5b

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

Quality

qwen3.5-9b-mlx

Reasoning
10/20
Coding
17/20
Instruction
5/20
Structured
9/15
Math
11/15
Multilingual
5/10
Reasoning: Weak Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Adequate Multilingual: Adequate

qwen2.5:0.5b

Reasoning
6/20
Coding
6/20
Instruction
7/20
Structured
11/15
Math
5/15
Multilingual
4/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Adequate Math: Weak Multilingual: Weak

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