Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
68 vs 80
Hardware Fit
93 vs 77
Quality Score
57 vs 81

Hardware

google/gemma-4-e4b qwen3.6:35b-mlx
MachineLENOVO 82JQMacBook Pro
CPUAMD Ryzen 7 5800HApple M5 Max
Cores1618
RAM16 GB48 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUApple M5 Max
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b qwen3.6:35b-mlx
Tokens/sec26.2129.8
First chunk17 ms77 ms
TTFT572 ms30.0 s
Load timeN/A1.8 s
Memory usage6.5 GB19.7 GB
Memory %41%41%

HW Fit Score Breakdown

google/gemma-4-e4b

Speed
46/50
TTFT
20/20
Memory
27/30

qwen3.6:35b-mlx

Speed
50/50
TTFT
0/20
Memory
27/30

Quality

google/gemma-4-e4b

Reasoning
17/20
Coding
19/20
Instruction
4/20
Structured
4/15
Math
12/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Weak Math: Strong Multilingual: Poor

qwen3.6:35b-mlx

Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate Math: Strong Multilingual: Strong
View google/gemma-4-e4b details | View qwen3.6:35b-mlx 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