Back to leaderboard

llama3.1:8b

llama · 8.0B · Q4_K_M

Not Rec.

Feb 28, 2026 · Apple M4 Pro

gemma2:2b

gemma2 · 2.6B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score
64 vs 72
Hardware Fit
56 vs 99
Quality Score
70 vs 54

Hardware

llama3.1:8b gemma2:2b
MachineMac MiniMacBook Air
CPUApple M4 ProApple M4
Cores1410
RAM64 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.7.4macOS 26.3
Archarm64arm64
Power Modeunknownbalanced

Performance

llama3.1:8b gemma2:2b
Tokens/sec5.553.8
TTFT1.4 s170 ms
Load time3.7 s0.6 s
Memory usage28.6 GB2.8 GB
Memory %45%9%

HW Fit Score Breakdown

llama3.1:8b

Speed
5/40
TTFT
22/30
Memory
29/30

gemma2:2b

Speed
40/40
TTFT
30/30
Memory
29/30

Quality

llama3.1:8b

Reasoning
12/20
Coding
17/20
Instruction
14/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

gemma2:2b

Reasoning
11/20
Coding
0/20
Instruction
14/20
Structured
15/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View llama3.1:8b details | View gemma2:2b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running