Back to leaderboard

gemma3:4b

gemma3 · 4.3B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

llama3.1:8b

llama · 8.0B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

Global Score
72 vs 69
Hardware Fit
99 vs 93
Quality Score
54 vs 53

Hardware

gemma3:4b 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

gemma3:4b llama3.1:8b
Tokens/sec35.920.2
TTFT303 ms481 ms
Load time0.2 s3.4 s
Memory usage4.6 GB10.4 GB
Memory %14%33%

HW Fit Score Breakdown

gemma3:4b

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

llama3.1:8b

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

Quality

gemma3:4b

Reasoning
11/20
Coding
0/20
Instruction
14/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

llama3.1:8b

Reasoning
12/20
Coding
0/20
Instruction
14/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View gemma3:4b details | View llama3.1:8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running