Back to leaderboard

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

gemma4:e2b

OLLAMA GGUF

gemma4 · 5.1B · Q4_K_M

Excellent

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score
53 vs 83
Hardware Fit
72 vs 100
Quality Score
45 vs 76

Hardware

qwen3.5:9b gemma4:e2b
MachineMacBook ProAZW GTR Pro
CPUApple M1 MaxAMD RYZEN AI MAX+ 395
Cores1032
RAM32 GB125 GB
GPUApple M1 MaxRadeon 8060S
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.5:9b gemma4:e2b
Tokens/sec18.688.1
First chunk403 ms193 ms
TTFT10.2 s193 ms
Load time4.3 s2.7 s
Memory usage9.1 GB11.2 GB
Memory %28%9%

HW Fit Score Breakdown

qwen3.5:9b

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

gemma4:e2b

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

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

gemma4:e2b

Reasoning
12/20
Coding
16/20
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
View qwen3.5:9b details | View gemma4:e2b 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