qwen3.5-2b-mlx
LM-STUDIO MLXqwen3_5 · 2B · 8bit
Mar 3, 2026 · Apple M4
qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Oct 11, 2026 · AMD Ryzen 5 5500
Global Score
70 vs 74
Hardware Fit
93 vs 100
Quality Score
60 vs 63
Hardware
qwen3.5-2b-mlx qwen3:0.6b
MachineMacBook AirMicrosoft WSL
CPUApple M4AMD Ryzen 5 5500
Cores1012
RAM32 GB8 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedunknown
Performance
qwen3.5-2b-mlx qwen3:0.6b
Tokens/sec32.9249.5
First chunk3096 ms80 ms
TTFT3.1 s659 ms
Load timeN/A6.3 s
Memory usage2.5 GB0.9 GB
Memory %8%11%
HW Fit Score Breakdown
qwen3.5-2b-mlx
Speed
50/50
TTFT
13/20
Memory
30/30
qwen3:0.6b
Speed
50/50
TTFT
20/20
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
qwen3:0.6b
Reasoning
13/20
Coding
6/20
Instruction
12/20
Structured
13/15
Math
12/15
Multilingual
7/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Adequate
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