qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
lfm2:24b-a2b
OLLAMA GGUFlfm2moe · 23.8B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
75 vs 78
Hardware Fit
50 vs 67
Quality Score
86 vs 82
Hardware
qwen2.5:72b lfm2:24b-a2b
MachineNVIDIA NVIDIA_DGX_SparkDell Inc. Inspiron 15 3530
CPUCortex-X925Intel Gen Intel® Core™ i7-1355U
Cores2012
RAM122 GB31 GB
GPUDevice 2e12Raptor Lake-P [Iris Xe Graphics]
OSUbuntu 24.04.4 LTScachyos rolling
Archarm64x64
Power Modeperformancelow-power
Performance
qwen2.5:72b lfm2:24b-a2b
Tokens/sec4.411.5
First chunk529 ms1727 ms
TTFT529 ms1.7 s
Load time49.7 s6.8 s
Memory usage54.0 GB13.9 GB
Memory %44%45%
HW Fit Score Breakdown
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
lfm2:24b-a2b
Speed
22/50
TTFT
19/20
Memory
26/30
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
lfm2:24b-a2b
Reasoning
13/20
Coding
17/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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