qwen3.5-9b-mlx
LM-STUDIO MLXqwen3_5 · 9B · 4bit
Mar 11, 2026 · Apple M4
smollm2:1.7b
OLLAMA GGUFllama · 1.7B · Q8_0
Mar 2, 2026 · Apple M4
Global Score
59 vs 64
Hardware Fit
65 vs 100
Quality Score
57 vs 49
Hardware
qwen3.5-9b-mlx smollm2:1.7b
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 smollm2:1.7b
Tokens/sec14.351.8
First chunk24 msN/A
TTFT13.4 s84 ms
Load time13.3 s0.4 s
Memory usage2.5 GB3.7 GB
Memory %10%12%
HW Fit Score Breakdown
qwen3.5-9b-mlx
Speed
32/50
TTFT
3/20
Memory
30/30
smollm2:1.7b
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
smollm2:1.7b
Reasoning
7/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
1/15
Multilingual
6/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest