meta-llama-3.1-8b-instruct

llama · 8B · 4bit

Good

Mar 3, 2026 · Apple M4

solar:10.7b

llama · 11B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

76 vs 63

Hardware Fit

95 vs 87

Quality Score

68 vs 52

Hardware

meta-llama-3.1-8b-… solar:10.7b

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-… solar:10.7b

Tokens/sec21.615.8

TTFT512 ms353 ms

Load time0.0 s0.4 s

Memory usage0.0 GB6.6 GB

Memory %0%21%

HW Fit Score Breakdown

meta-llama-3.1-8b-instr…

Speed

35/40

TTFT

30/30

Memory

30/30

solar:10.7b

Speed

27/40

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

solar:10.7b

Reasoning

8/20

Coding

8/20

Instruction

11/20

Structured

14/15

Math

4/15

Multilingual

7/10

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

View meta-llama-3.1-8b-… details | View solar:10.7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running