qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
maternion/ling-3.0-tiny:8b
OLLAMA GGUFbailingmoe3 · 7.9B · Q4_K_M
Aug 26, 2026 · Apple M1 Pro
Global Score
75 vs 68
Hardware Fit
50 vs 98
Quality Score
86 vs 55
Hardware
qwen2.5:72b maternion/ling-3.0…
MachineNVIDIA NVIDIA_DGX_SparkMacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced
Performance
qwen2.5:72b maternion/ling-3.0…
Tokens/sec4.472.1
First chunk529 ms175 ms
TTFT529 ms175 ms
Load time49.7 s3.6 s
Memory usage54.0 GB5.9 GB
Memory %44%37%
HW Fit Score Breakdown
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
maternion/ling-3.0-tiny…
Speed
50/50
TTFT
20/20
Memory
28/30
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
maternion/ling-3.0-tiny…
Reasoning
19/20
Coding
17/20
Instruction
3/20
Structured
0/15
Math
15/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor
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