ministral-3:8b

OLLAMA GGUF

mistral3 · 8.9B · Q4_K_M

Good

Jun 25, 2026 · Apple M4 Pro

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Good

Mar 2, 2026 · Apple M4

Global Score

79 vs 65

Hardware Fit

98 vs 99

Quality Score

71 vs 51

Hardware

ministral-3:8b qwen3.5:0.8b

MachineMac miniMacBook Air

CPUApple M4 ProApple M4

Cores1210

RAM24 GB32 GB

GPUApple M4 ProApple M4

OSmacOS 15.6.1macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

ministral-3:8b qwen3.5:0.8b

Tokens/sec41.448.2

First chunk257 msN/A

TTFT257 ms195 ms

Load time5.2 s1.0 s

Memory usage9.0 GB2.5 GB

Memory %38%8%

HW Fit Score Breakdown

ministral-3:8b

Speed

50/50

TTFT

20/20

Memory

28/30

qwen3.5:0.8b

Speed

40/50

TTFT

30/20

Memory

29/30

Quality

ministral-3:8b

Reasoning

12/20

Coding

18/20

Instruction

12/20

Structured

13/15

Math

6/15

Multilingual

10/10

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

qwen3.5:0.8b

Reasoning

9/20

Coding

6/20

Instruction

11/20

Structured

13/15

Math

5/15

Multilingual

7/10

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

View ministral-3:8b details | View qwen3.5:0.8b details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest