qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
qwen3.5-4b-mlx
LM-STUDIO MLXqwen3_5 · 4B · 4bit
Mar 6, 2026 · Apple M4 Pro
Global Score
75 vs 62
Hardware Fit
50 vs 35
Quality Score
86 vs 73
Hardware
qwen2.5:72b qwen3.5-4b-mlx
MachineNVIDIA NVIDIA_DGX_SparkMac mini
CPUCortex-X925Apple M4 Pro
Cores2014
RAM122 GB64 GB
GPUDevice 2e12Apple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 15.7.4
Archarm64arm64
Power Modeperformancebalanced
Performance
qwen2.5:72b qwen3.5-4b-mlx
Tokens/sec4.40.0
First chunk529 ms5548 ms
TTFT529 ms5.5 s
Load time49.7 sN/A
Memory usage54.0 GB2.9 GB
Memory %44%5%
HW Fit Score Breakdown
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
qwen3.5-4b-mlx
Speed
0/50
TTFT
6/20
Memory
29/30
Quality
qwen2.5:72b
Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.5-4b-mlx
Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate 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