qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
qwen3.8-27b-mlx
LM-STUDIO UNKNOWN27B
Aug 17, 2026 · Apple M5 Max
Global Score
75 vs 66
Hardware Fit
50 vs 91
Quality Score
86 vs 55
Hardware
qwen2.5:72b qwen3.8-27b-mlx
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M5 Max
Cores2018
RAM122 GB64 GB
GPUDevice 2e12Apple M5 Max
OSUbuntu 24.04.4 LTSmacOS 27.0
Archarm64arm64
Power Modeperformancebalanced
Performance
qwen2.5:72b qwen3.8-27b-mlx
Tokens/sec4.433.2
First chunk529 ms7 ms
TTFT529 ms311 ms
Load time49.7 sN/A
Memory usage54.0 GB0.5 GB
Memory %44%1%
HW Fit Score Breakdown
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
qwen3.8-27b-mlx
Speed
41/50
TTFT
20/20
Memory
30/30
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
qwen3.8-27b-mlx
Reasoning
19/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
3/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor 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