Back to leaderboard

gemma4:e4b-mlx

OLLAMA GGUF
Excellent

Jul 7, 2026 · Apple M2 Pro

smollm2-135m-instruct

LM-STUDIO GGUF

llama · 135M · Q4_K_M

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

Global Score
85 vs 38
Hardware Fit
95 vs 98
Quality Score
81 vs 12

Hardware

gemma4:e4b-mlx smollm2-135m-instr…
MachineMacBook ProLENOVO 20BUS00700
CPUApple M2 ProIntel Core™ i5-5300U
Cores104
RAM16 GB16 GB
GPUApple M2 ProIntel(R) HD Graphics 5500
OSmacOS 26.5Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced

Performance

gemma4:e4b-mlx smollm2-135m-instr…
Tokens/sec47.339.3
First chunk258 ms573 ms
TTFT258 ms573 ms
Load time5.1 sN/A
Memory usage7.9 GB0.1 GB
Memory %49%1%

HW Fit Score Breakdown

gemma4:e4b-mlx

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

smollm2-135m-instruct

Speed
50/50
TTFT
20/20
Memory
28/30

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

smollm2-135m-instruct

Reasoning
2/20
Coding
1/20
Instruction
5/20
Structured
3/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
View gemma4:e4b-mlx details | View smollm2-135m-instr… 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