llama3.1:8b

llama · 8.0B · Q4_K_M

Not Rec.

Feb 28, 2026 · Apple M4 Pro

qwen3:8b

qwen3 · 8.2B · Q4_K_M

Marginal

Mar 2, 2026 · Apple M4

Global Score

64 vs 50

Hardware Fit

56 vs 67

Quality Score

70 vs 38

Hardware

llama3.1:8b qwen3:8b

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 qwen3:8b

Tokens/sec5.518.7

TTFT1.4 s12.1 s

Load time3.7 s1.2 s

Memory usage28.6 GB9.5 GB

Memory %45%30%

HW Fit Score Breakdown

llama3.1:8b

Speed

5/40

TTFT

22/30

Memory

29/30

qwen3:8b

Speed

31/40

TTFT

6/30

Memory

30/30

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

qwen3:8b

Reasoning

5/20

Coding

5/20

Instruction

4/20

Structured

12/15

Math

2/15

Multilingual

10/10

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

View llama3.1:8b details | View qwen3:8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running