Back to leaderboard

gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Excellent

Jul 4, 2026 · Apple M2 Pro

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score
89 vs 64
Hardware Fit
88 vs 69
Quality Score
89 vs 62

Hardware

gemma4:12b qwen3.5:4b
MachineMacBook ProLENOVO 20U30029MB
CPUApple M2 ProIntel Core™ i5-10210U
Cores108
RAM16 GB15 GB
GPUApple M2 ProCometLake-U GT2 [UHD Graphics]
OSmacOS 26.5Pop 24.04 LTS
Archarm64x64
Power Modebalancedperformance

Performance

gemma4:12b qwen3.5:4b
Tokens/sec18.47.4
First chunk758 ms1815 ms
TTFT758 ms1.8 s
Load time0.3 s10.9 s
Memory usage7.5 GB3.5 GB
Memory %47%23%

HW Fit Score Breakdown

gemma4:12b

Speed
42/50
TTFT
20/20
Memory
26/30

qwen3.5:4b

Speed
19/50
TTFT
20/20
Memory
30/30

Quality

gemma4:12b

Reasoning
17/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5:4b

Reasoning
15/20
Coding
14/20
Instruction
6/20
Structured
12/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong
View gemma4:12b details | View qwen3.5:4b 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