Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · Q4_K_M

Good

Jul 7, 2026 · AMD Ryzen 7 5800H

Global Score
53 vs 62
Hardware Fit
72 vs 77
Quality Score
45 vs 55

Hardware

qwen3.5:9b google/gemma-4-e4b
MachineMacBook ProLENOVO 82JQ
CPUApple M1 MaxAMD Ryzen 7 5800H
Cores1016
RAM32 GB16 GB
GPUApple M1 MaxNVIDIA GeForce RTX 3060 Laptop GPU
OSmacOS 26.3Microsoft Windows 11 家庭版 中文版 10.0.26100
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3.5:9b google/gemma-4-e4b
Tokens/sec18.627.6
First chunk403 ms23 ms
TTFT10.2 s480 ms
Load time4.3 sN/A
Memory usage9.1 GB13.2 GB
Memory %28%83%

HW Fit Score Breakdown

qwen3.5:9b

Speed
38/50
TTFT
4/20
Memory
30/30

google/gemma-4-e4b

Speed
48/50
TTFT
20/20
Memory
9/30

Quality

qwen3.5:9b

Reasoning
12/20
Coding
3/20
Instruction
5/20
Structured
6/15
Math
11/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong

google/gemma-4-e4b

Reasoning
18/20
Coding
17/20
Instruction
5/20
Structured
3/15
Math
11/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
View qwen3.5:9b details | View google/gemma-4-e4b 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