Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

Global Score
68 vs 58
Hardware Fit
93 vs 68
Quality Score
57 vs 54

Hardware

google/gemma-4-e4b qwen3.5-9b-mlx
MachineLENOVO 82JQMac mini
CPUAMD Ryzen 7 5800HApple M4
Cores1610
RAM16 GB24 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUApple M4
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b qwen3.5-9b-mlx
Tokens/sec26.216.7
First chunk17 ms23 ms
TTFT572 ms14.1 s
Load timeN/AN/A
Memory usage6.5 GB7.8 GB
Memory %41%33%

HW Fit Score Breakdown

google/gemma-4-e4b

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

qwen3.5-9b-mlx

Speed
36/50
TTFT
3/20
Memory
29/30

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

qwen3.5-9b-mlx

Reasoning
10/20
Coding
16/20
Instruction
4/20
Structured
9/15
Math
10/15
Multilingual
5/10
Reasoning: Adequate Coding: Strong Instruction Following: Poor Structured Output: Adequate Math: Adequate Multilingual: Adequate
View google/gemma-4-e4b details | View qwen3.5-9b-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