Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

qwen3-vl-4b-instruct

LM-STUDIO GGUF

qwen3vl · 4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

Global Score
68 vs 87
Hardware Fit
93 vs 100
Quality Score
57 vs 81

Hardware

google/gemma-4-e4b qwen3-vl-4b-instruct
MachineLENOVO 82JQMac Studio
CPUAMD Ryzen 7 5800HApple M2 Max
Cores1612
RAM16 GB96 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUApple M2 Max
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100macOS 26.1
Archx64arm64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b qwen3-vl-4b-instruct
Tokens/sec26.271.2
First chunk17 ms4 ms
TTFT572 ms156 ms
Load timeN/AN/A
Memory usage6.5 GB20.5 GB
Memory %41%21%

HW Fit Score Breakdown

google/gemma-4-e4b

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

qwen3-vl-4b-instruct

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

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-vl-4b-instruct

Reasoning
15/20
Coding
17/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

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