codellama:7b

llama · 7B · Q4_0

Good

Mar 1, 2026 · Apple M4

qwen3:0.6b

qwen3 · 751.63M · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score

63 vs 61

Hardware Fit

97 vs 100

Quality Score

49 vs 44

Hardware

codellama:7b qwen3:0.6b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

codellama:7b qwen3:0.6b

Tokens/sec23.6144.3

TTFT297 ms81 ms

Load time0.9 s0.9 s

Memory usage12.6 GB4.1 GB

Memory %39%13%

HW Fit Score Breakdown

codellama:7b

Speed

37/40

TTFT

30/30

Memory

30/30

qwen3:0.6b

Speed

40/40

TTFT

30/30

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

qwen3:0.6b

Reasoning

6/20

Coding

4/20

Instruction

10/20

Structured

13/15

Math

6/15

Multilingual

5/10

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

View codellama:7b details | View qwen3:0.6b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running