Back to leaderboard

deepseek-v2:16b

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

tinyllama:1.1b

llama · 1B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score
69 vs 43
Hardware Fit
100 vs 100
Quality Score
55 vs 19

Hardware

deepseek-v2:16b tinyllama:1.1b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

deepseek-v2:16b tinyllama:1.1b
Tokens/sec56.6121.0
TTFT239 ms82 ms
Load time1.2 s0.4 s
Memory usage17.7 GB0.7 GB
Memory %55%2%

HW Fit Score Breakdown

deepseek-v2:16b

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

tinyllama:1.1b

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

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

tinyllama:1.1b

Reasoning
2/20
Coding
1/20
Instruction
6/20
Structured
7/15
Math
0/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
View deepseek-v2:16b details | View tinyllama:1.1b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running