Back to leaderboard

deepseek-v2:16b

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

gemma3:1b

gemma3 · 999.89M · Q4_K_M

Good

Feb 28, 2026 · Apple M4

Global Score
73 vs 72
Hardware Fit
100 vs 98
Quality Score
55 vs 55

Hardware

deepseek-v2:16b gemma3:1b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedunknown

Performance

deepseek-v2:16b gemma3:1b
Tokens/sec56.639.5
TTFT239 ms333 ms
Load time1.2 s1.6 s
Memory usage17.7 GB1.3 GB
Memory %55%4%

HW Fit Score Breakdown

deepseek-v2:16b

Speed
40/40
TTFT
30/30
Memory
30/30

gemma3:1b

Speed
40/40
TTFT
30/30
Memory
28/30

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

gemma3:1b

Reasoning
6/20
Coding
13/20
Instruction
15/20
Structured
12/15
Math
1/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
View deepseek-v2:16b details | View gemma3:1b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running