Back to leaderboard

gemma4:e4b-mlx

OLLAMA GGUF
Excellent

Jul 7, 2026 · Apple M2 Pro

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
85 vs 61
Hardware Fit
95 vs 85
Quality Score
81 vs 51

Hardware

gemma4:e4b-mlx qwen3:0.6b
MachineMacBook ProLENOVO 20L7CTO1WW
CPUApple M2 ProIntel Core™ i5-8350U
Cores108
RAM16 GB23 GB
GPUApple M2 ProKaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 26.5Fedora Linux 43
Archarm64x64
Power Modebalancedlow-power

Performance

gemma4:e4b-mlx qwen3:0.6b
Tokens/sec47.327.0
First chunk258 ms597 ms
TTFT258 ms8.7 s
Load time5.1 s1.8 s
Memory usage7.9 GB0.9 GB
Memory %49%4%

HW Fit Score Breakdown

gemma4:e4b-mlx

Speed
50/50
TTFT
20/20
Memory
25/30

qwen3:0.6b

Speed
50/50
TTFT
5/20
Memory
30/30

Quality

gemma4:e4b-mlx

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

qwen3:0.6b

Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate
View gemma4:e4b-mlx details | View qwen3:0.6b 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