Back to leaderboard

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

liquid/lfm2-24b-a2b

LM-STUDIO MLX

lfm2_moe · 24B · 4bit

Good

Mar 19, 2026 · Apple M4

Global Score
75 vs 74
Hardware Fit
50 vs 84
Quality Score
86 vs 69

Hardware

qwen2.5:72b liquid/lfm2-24b-a2b
MachineNVIDIA NVIDIA_DGX_SparkMac mini
CPUCortex-X925Apple M4
Cores2010
RAM122 GB24 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced

Performance

qwen2.5:72b liquid/lfm2-24b-a2b
Tokens/sec4.458.9
First chunk529 ms28 ms
TTFT529 ms481 ms
Load time49.7 sN/A
Memory usage54.0 GB17.5 GB
Memory %44%73%

HW Fit Score Breakdown

qwen2.5:72b

Speed
4/50
TTFT
20/20
Memory
26/30

liquid/lfm2-24b-a2b

Speed
50/50
TTFT
20/20
Memory
14/30

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

liquid/lfm2-24b-a2b

Reasoning
11/20
Coding
12/20
Instruction
16/20
Structured
13/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest