Back to leaderboard

deepseek-v2:16b

OLLAMA GGUF

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Not Rec.

Aug 22, 2026 · Apple M1 Pro

Global Score
69 vs 63
Hardware Fit
100 vs 62
Quality Score
55 vs 63

Hardware

deepseek-v2:16b gemma4:12b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

deepseek-v2:16b gemma4:12b
Tokens/sec56.615.3
First chunkN/A1142 ms
TTFT239 ms30.0 s
Load time1.2 s5.4 s
Memory usage17.7 GB7.6 GB
Memory %55%47%

HW Fit Score Breakdown

deepseek-v2:16b

Speed
40/50
TTFT
30/20
Memory
30/30

gemma4:12b

Speed
36/50
TTFT
0/20
Memory
26/30

Quality

deepseek-v2:16b

Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
10/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong

gemma4:12b

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

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