Back to leaderboard

mlx-community/gemma-3-4b-it-qat-4bit

LM-STUDIO GGUF
Excellent

Mar 5, 2026 · Apple M4

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

Global Score
80 vs 75
Hardware Fit
100 vs 50
Quality Score
71 vs 86

Hardware

mlx-community/gemm… qwen2.5:72b
MachineMacBook AirNVIDIA NVIDIA_DGX_Spark
CPUApple M4Cortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance

Performance

mlx-community/gemm… qwen2.5:72b
Tokens/sec43.24.4
First chunk428 ms529 ms
TTFT428 ms529 ms
Load timeN/A49.7 s
Memory usage1.3 GB54.0 GB
Memory %4%44%

HW Fit Score Breakdown

mlx-community/gemma-3-4…

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

qwen2.5:72b

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

Quality

mlx-community/gemma-3-4…

Reasoning
9/20
Coding
17/20
Instruction
17/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

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
View mlx-community/gemm… details | View qwen2.5:72b details

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