Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

llama2:13b

OLLAMA GGUF

llama · 13B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score
58 vs 56
Hardware Fit
68 vs 84
Quality Score
54 vs 44

Hardware

qwen3.5-9b-mlx llama2:13b
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 llama2:13b
Tokens/sec16.713.5
First chunk23 msN/A
TTFT14.1 s415 ms
Load timeN/A0.6 s
Memory usage7.8 GB10.3 GB
Memory %33%32%

HW Fit Score Breakdown

qwen3.5-9b-mlx

Speed
36/50
TTFT
3/20
Memory
29/30

llama2:13b

Speed
24/50
TTFT
30/20
Memory
30/30

Quality

qwen3.5-9b-mlx

Reasoning
10/20
Coding
16/20
Instruction
4/20
Structured
9/15
Math
10/15
Multilingual
5/10
Reasoning: Adequate Coding: Strong Instruction Following: Poor Structured Output: Adequate Math: Adequate Multilingual: Adequate

llama2:13b

Reasoning
9/20
Coding
3/20
Instruction
13/20
Structured
7/15
Math
3/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Poor 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