qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 4bit
Oct 20, 2026 · Apple M1 Pro
lfm2.5-1.2b-instruct-mlx
LM-STUDIO MLXlfm2 · 1.2B · 8bit
Mar 4, 2026 · Apple M4
Global Score
78 vs 68
Hardware Fit
56 vs 100
Quality Score
87 vs 54
Hardware
qwen3.8-27b-mlx lfm2.5-1.2b-instru…
MachineMacBook ProMacBook Air
CPUApple M1 ProApple M4
Cores1010
RAM32 GB32 GB
GPUApple M1 ProApple M4
OSmacOS 15.6.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.8-27b-mlx lfm2.5-1.2b-instru…
Tokens/sec10.877.3
First chunk8 ms177 ms
TTFT2.6 s177 ms
Load timeN/AN/A
Memory usage21.0 GB1.2 GB
Memory %66%4%
HW Fit Score Breakdown
qwen3.8-27b-mlx
Speed
23/50
TTFT
16/20
Memory
17/30
lfm2.5-1.2b-instruct-mlx
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.8-27b-mlx
Reasoning
18/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong 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