qwen3.5-2b-mlx
LM-STUDIO MLXqwen3_5 · 2B · 8bit
Mar 3, 2026 · Apple M4
openai/gpt-oss-20b
LM-STUDIO MLXgpt_oss · 20B · MXFP4
Mar 11, 2026 · Apple M4
Global Score
70 vs 95
Hardware Fit
93 vs 99
Quality Score
60 vs 93
Hardware
qwen3.5-2b-mlx openai/gpt-oss-20b
MachineMacBook AirMac mini
CPUApple M4Apple M4
Cores1010
RAM32 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-2b-mlx openai/gpt-oss-20b
Tokens/sec32.929.3
First chunk3096 ms21 ms
TTFT3.1 s1.8 s
Load timeN/A18.5 s
Memory usage2.5 GB0.0 GB
Memory %8%0%
HW Fit Score Breakdown
qwen3.5-2b-mlx
Speed
50/50
TTFT
13/20
Memory
30/30
openai/gpt-oss-20b
Speed
50/50
TTFT
19/20
Memory
30/30
Quality
qwen3.5-2b-mlx
Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
openai/gpt-oss-20b
Reasoning
19/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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