qwen3.5-9b-mlx
LM-STUDIO MLXqwen3_5 · 9B · 4bit
Mar 12, 2026 · Apple M4 Pro
lfm2.5-1.2b-instruct-mlx
LM-STUDIO MLXlfm2 · 1.2B · 8bit
Mar 4, 2026 · Apple M4
Global Score
77 vs 68
Hardware Fit
67 vs 100
Quality Score
81 vs 54
Hardware
qwen3.5-9b-mlx lfm2.5-1.2b-instru…
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-9b-mlx lfm2.5-1.2b-instru…
Tokens/sec20.377.3
First chunk4216 ms177 ms
TTFT4.2 s177 ms
Load timeN/AN/A
Memory usage5.6 GB1.2 GB
Memory %9%4%
HW Fit Score Breakdown
qwen3.5-9b-mlx
Speed
29/50
TTFT
8/20
Memory
30/30
lfm2.5-1.2b-instruct-mlx
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
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
lfm2.5-1.2b-instruct-mlx
Reasoning
10/20
Coding
7/20
Instruction
16/20
Structured
12/15
Math
1/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Poor 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