qwen3.5-4b-mlx
LM-STUDIO MLXqwen3_5 · 4B · 4bit
Mar 3, 2026 · Apple M4
deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
71 vs 60
Hardware Fit
88 vs 90
Quality Score
63 vs 47
Hardware
qwen3.5-4b-mlx deepseek-r1:1.5b
MachineMacBook AirNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4Cortex-A78AE
Cores106
RAM32 GB7 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-4b-mlx deepseek-r1:1.5b
Tokens/sec23.134.6
First chunk3279 ms5314 ms
TTFT3.3 s5.3 s
Load timeN/A5.1 s
Memory usage2.9 GB1.1 GB
Memory %9%15%
HW Fit Score Breakdown
qwen3.5-4b-mlx
Speed
45/50
TTFT
13/20
Memory
30/30
deepseek-r1:1.5b
Speed
50/50
TTFT
10/20
Memory
30/30
Quality
qwen3.5-4b-mlx
Reasoning
15/20
Coding
16/20
Instruction
6/20
Structured
6/15
Math
11/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong
deepseek-r1:1.5b
Reasoning
11/20
Coding
6/20
Instruction
7/20
Structured
4/15
Math
14/15
Multilingual
5/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Weak
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