Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

llama3:latest

OLLAMA GGUF

llama · 8.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
59 vs 71
Hardware Fit
65 vs 95
Quality Score
57 vs 60

Hardware

qwen3.5-9b-mlx llama3:latest
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 llama3:latest
Tokens/sec14.322.3
First chunk24 msN/A
TTFT13.4 s295 ms
Load time13.3 s0.8 s
Memory usage2.5 GB5.6 GB
Memory %10%18%

HW Fit Score Breakdown

qwen3.5-9b-mlx

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

llama3:latest

Speed
35/50
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

llama3:latest

Reasoning
9/20
Coding
9/20
Instruction
15/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Weak 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