Back to leaderboard

llama2:13b

llama · 13B · Q4_0

Good

Mar 2, 2026 · Apple M4

llama3.1:8b

llama · 8.0B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score
60 vs 77
Hardware Fit
84 vs 93
Quality Score
44 vs 67

Hardware

llama2:13b llama3.1:8b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

llama2:13b llama3.1:8b
Tokens/sec13.520.3
TTFT415 ms315 ms
Load time0.6 s1.1 s
Memory usage10.3 GB10.4 GB
Memory %32%33%

HW Fit Score Breakdown

llama2:13b

Speed
24/40
TTFT
30/30
Memory
30/30

llama3.1:8b

Speed
33/40
TTFT
30/30
Memory
30/30

Quality

llama2:13b

Reasoning
9/20
Coding
3/20
Instruction
13/20
Structured
7/15
Math
3/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Poor Multilingual: Strong

llama3.1:8b

Reasoning
12/20
Coding
15/20
Instruction
13/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View llama2:13b details | View llama3.1:8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running