lfm2.5-1.2b-instruct-mlx
LM-STUDIO MLXlfm2 · 1.2B · 8bit
Mar 4, 2026 · Apple M4
qwen3.5-9b
LM-STUDIO MLXqwen3_5 · 9B · 4bit
Mar 3, 2026 · Apple M4
Global Score
68 vs 81
Hardware Fit
100 vs 84
Quality Score
54 vs 79
Hardware
lfm2.5-1.2b-instru… qwen3.5-9b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
lfm2.5-1.2b-instru… qwen3.5-9b
Tokens/sec77.320.4
First chunk177 ms3034 ms
TTFT177 ms3.0 s
Load timeN/AN/A
Memory usage1.2 GB5.6 GB
Memory %4%17%
HW Fit Score Breakdown
lfm2.5-1.2b-instruct-mlx
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5-9b
Speed
41/50
TTFT
14/20
Memory
29/30
Quality
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
qwen3.5-9b
Reasoning
14/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
10/15
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