meta-llama-3.1-8b-instruct

llama · 8B · 4bit

Good

Mar 3, 2026 · Apple M4

deepseek-coder:6.7b

llama · 7B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score

76 vs 57

Hardware Fit

95 vs 98

Quality Score

68 vs 39

Hardware

meta-llama-3.1-8b-… deepseek-coder:6.7b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

meta-llama-3.1-8b-… deepseek-coder:6.7b

Tokens/sec21.624.1

TTFT512 ms251 ms

Load time0.0 s0.9 s

Memory usage0.0 GB12.6 GB

Memory %0%39%

HW Fit Score Breakdown

meta-llama-3.1-8b-instr…

Speed

35/40

TTFT

30/30

Memory

30/30

deepseek-coder:6.7b

Speed

38/40

TTFT

30/30

Memory

30/30

Quality

meta-llama-3.1-8b-instr…

Reasoning

11/20

Coding

15/20

Instruction

14/20

Structured

14/15

Math

4/15

Multilingual

10/10

Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

deepseek-coder:6.7b

Reasoning

4/20

Coding

14/20

Instruction

9/20

Structured

6/15

Math

1/15

Multilingual

5/10

Reasoning: Poor Coding: Adequate Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak

View meta-llama-3.1-8b-… details | View deepseek-coder:6.7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running