Back to leaderboard

gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Excellent

Jul 4, 2026 · Apple M2 Pro

qwen/qwen3.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q6_K

Not Rec.

Sep 19, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
89 vs 72
Hardware Fit
88 vs 35
Quality Score
89 vs 88

Hardware

gemma4:12b qwen/qwen3.5-35b-a3b
MachineMacBook ProSystem manufacturer
CPUApple M2 ProAMD Ryzen 7 5800X 8-Core Processor
Cores1016
RAM16 GB32 GB
GPUApple M2 ProAMD Radeon RX 9060 XT
OSmacOS 26.5Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

gemma4:12b qwen/qwen3.5-35b-a3b
Tokens/sec18.48.3
First chunk758 ms32 ms
TTFT758 ms2.0 s
Load time0.3 sN/A
Memory usage7.5 GB28.9 GB
Memory %47%91%

HW Fit Score Breakdown

gemma4:12b

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

qwen/qwen3.5-35b-a3b

Speed
13/50
TTFT
17/20
Memory
5/30

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

qwen/qwen3.5-35b-a3b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gemma4:12b details | View qwen/qwen3.5-35b-a3b 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