mistral:7b

llama · 7.2B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

tinyllama:1.1b

llama · 1B · Q4_0

Marginal

Mar 1, 2026 · Apple M4

Global Score

61 vs 50

Hardware Fit

81 vs 99

Quality Score

48 vs 18

Hardware

mistral:7b tinyllama:1.1b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

mistral:7b tinyllama:1.1b

Tokens/sec13.6129.6

TTFT517 ms58 ms

Load time3.0 s0.4 s

Memory usage10.1 GB0.7 GB

Memory %32%2%

HW Fit Score Breakdown

mistral:7b

Speed

21/40

TTFT

30/30

Memory

30/30

tinyllama:1.1b

Speed

40/40

TTFT

30/30

Memory

29/30

Quality

mistral:7b

Reasoning

8/20

Coding

0/20

Instruction

12/20

Structured

14/15

Math

5/15

Multilingual

9/10

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

tinyllama:1.1b

Reasoning

2/20

Coding

0/20

Instruction

6/20

Structured

7/15

Math

0/15

Multilingual

3/10

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

View mistral:7b details | View tinyllama:1.1b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running