Back to leaderboard

hf.co/unsloth/gemma-4-E2B-it-GGUF:UD-Q8_K_XL

OLLAMA GGUF

gemma4 · 4.65B · unknown

Excellent

Aug 23, 2026 · Apple M1 Pro

mlx-community/gemma-3-1b-it-8bit

LM-STUDIO GGUF
Good

Mar 5, 2026 · Apple M4

Global Score
84 vs 72
Hardware Fit
99 vs 99
Quality Score
77 vs 61

Hardware

hf.co/unsloth/gemm… mlx-community/gemm…
MachineMacBook ProMacBook Air
CPUApple M1 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M1 ProApple M4
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

hf.co/unsloth/gemm… mlx-community/gemm…
Tokens/sec48.086.3
First chunk167 ms253 ms
TTFT167 ms253 ms
Load time4.7 sN/A
Memory usage5.3 GB1.1 GB
Memory %33%4%

HW Fit Score Breakdown

hf.co/unsloth/gemma-4-E…

Speed
50/50
TTFT
20/20
Memory
29/30

mlx-community/gemma-3-1…

Speed
50/50
TTFT
20/20
Memory
29/30

Quality

hf.co/unsloth/gemma-4-E…

Reasoning
12/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

mlx-community/gemma-3-1…

Reasoning
7/20
Coding
14/20
Instruction
16/20
Structured
14/15
Math
2/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
View hf.co/unsloth/gemm… details | View mlx-community/gemm… 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