Back to leaderboard

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

tinyllama:1.1b

OLLAMA GGUF

llama · 1B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score
59 vs 43
Hardware Fit
65 vs 100
Quality Score
57 vs 19

Hardware

qwen3.5-9b-mlx tinyllama:1.1b
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 tinyllama:1.1b
Tokens/sec14.3121.0
First chunk24 msN/A
TTFT13.4 s82 ms
Load time13.3 s0.4 s
Memory usage2.5 GB0.7 GB
Memory %10%2%

HW Fit Score Breakdown

qwen3.5-9b-mlx

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

tinyllama:1.1b

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

tinyllama:1.1b

Reasoning
2/20
Coding
1/20
Instruction
6/20
Structured
7/15
Math
0/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor 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