Back to leaderboard

gemma4:12b-mlx

OLLAMA GGUF
Not Rec.

Aug 24, 2026 · Apple M1 Pro

qwen/qwen3.6-35b-a3b

LM-STUDIO MLX

qwen3_5_moe · 35B · 6bit

Excellent

Jul 17, 2026 · Apple M5 Max

Global Score
71 vs 87
Hardware Fit
76 vs 90
Quality Score
69 vs 86

Hardware

gemma4:12b-mlx qwen/qwen3.6-35b-a3b
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M5 Max
Cores1018
RAM16 GB64 GB
GPUApple M1 ProApple M5 Max
OSmacOS 26.6.2macOS 27.0
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:12b-mlx qwen/qwen3.6-35b-a3b
Tokens/sec25.086.5
First chunk787 ms9 ms
TTFT30.0 s175 ms
Load time4.0 sN/A
Memory usage7.1 GB37.9 GB
Memory %45%59%

HW Fit Score Breakdown

gemma4:12b-mlx

Speed
50/50
TTFT
0/20
Memory
26/30

qwen/qwen3.6-35b-a3b

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

Quality

gemma4:12b-mlx

Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Strong

qwen/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
15/20
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-mlx details | View qwen/qwen3.6-35b-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