qwen3.5-2b-mlx
LM-STUDIO MLXqwen3_5 · 2B · 8bit
Mar 3, 2026 · Apple M4
gptoss · 20.9B · MXFP4
OLLAMA GGUFgptoss · 20.9 · MXFP4
Jul 9, 2026 · Intel Core™ i5-10400
Global Score
70 vs 84
Hardware Fit
93 vs 69
Quality Score
60 vs 91
Hardware
qwen3.5-2b-mlx gptoss · 20.9B · M…
MachineMacBook AirMac Pro
CPUApple M4Intel Core™ i5-10400
Cores1012
RAM32 GB32 GB
GPUApple M4AMD Radeon RX 6700 XT
OSmacOS 26.3macOS 26.5.1
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.5-2b-mlx gptoss · 20.9B · M…
Tokens/sec32.917.5
First chunk3096 ms643 ms
TTFT3.1 s7.7 s
Load timeN/A0.0 s
Memory usage2.5 GB0.8 GB
Memory %8%3%
HW Fit Score Breakdown
qwen3.5-2b-mlx
Speed
50/50
TTFT
13/20
Memory
30/30
gptoss · 20.9B · MXFP4
Speed
34/50
TTFT
5/20
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
gptoss · 20.9B · MXFP4
Reasoning
19/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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