smollm2-1.7b-instruct
LM-STUDIO MLXllama · 1.7B · bf16
Mar 4, 2026 · Apple M4
qwen3.5-9b-mlx
LM-STUDIO MLXqwen3_5 · 9B · 4bit
Mar 12, 2026 · Apple M4 Pro
Global Score
65 vs 77
Hardware Fit
99 vs 67
Quality Score
51 vs 81
Hardware
smollm2-1.7b-instr… qwen3.5-9b-mlx
MachineMacBook AirMac mini
CPUApple M4Apple M4 Pro
Cores1014
RAM32 GB64 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced
Performance
smollm2-1.7b-instr… qwen3.5-9b-mlx
Tokens/sec28.520.3
First chunk393 ms4216 ms
TTFT393 ms4.2 s
Load timeN/AN/A
Memory usage3.2 GB5.6 GB
Memory %10%9%
HW Fit Score Breakdown
smollm2-1.7b-instruct
Speed
50/50
TTFT
20/20
Memory
29/30
qwen3.5-9b-mlx
Speed
29/50
TTFT
8/20
Memory
30/30
Quality
smollm2-1.7b-instruct
Reasoning
10/20
Coding
10/20
Instruction
13/20
Structured
11/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Adequate
qwen3.5-9b-mlx
Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
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