codellama:7b

llama · 7B · Q4_0

Good

Mar 1, 2026 · Apple M4

qwen3:8b

qwen3 · 8.2B · Q4_K_M

Not Rec.

Mar 1, 2026 · Apple M4

Global Score

63 vs 39

Hardware Fit

97 vs 60

Quality Score

49 vs 30

Hardware

codellama:7b qwen3:8b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedunknown

Performance

codellama:7b qwen3:8b

Tokens/sec23.618.2

TTFT297 ms12.4 s

Load time0.9 s2.7 s

Memory usage12.6 GB9.5 GB

Memory %39%30%

HW Fit Score Breakdown

codellama:7b

Speed

37/40

TTFT

30/30

Memory

30/30

qwen3:8b

Speed

27/40

TTFT

3/30

Memory

30/30

Quality

codellama:7b

Reasoning

6/20

Coding

7/20

Instruction

12/20

Structured

13/15

Math

3/15

Multilingual

8/10

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

qwen3:8b

Reasoning

9/20

Coding

0/20

Instruction

5/20

Structured

4/15

Math

3/15

Multilingual

9/10

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

View codellama:7b details | View qwen3:8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running