qwen3.5-9b-mlx
LM-STUDIO MLXqwen3_5 · 9B · 4bit
Mar 11, 2026 · Apple M4
ministral-3:8b
OLLAMA GGUFmistral3 · 8.9B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
Global Score
58 vs 72
Hardware Fit
68 vs 71
Quality Score
54 vs 72
Hardware
qwen3.5-9b-mlx ministral-3:8b
MachineMac miniMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM24 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-9b-mlx ministral-3:8b
Tokens/sec16.719.8
First chunk23 ms269 ms
TTFT14.1 s269 ms
Load timeN/A10.7 s
Memory usage7.8 GB13.7 GB
Memory %33%86%
HW Fit Score Breakdown
qwen3.5-9b-mlx
Speed
36/50
TTFT
3/20
Memory
29/30
ministral-3:8b
Speed
44/50
TTFT
20/20
Memory
7/30
Quality
qwen3.5-9b-mlx
Reasoning
10/20
Coding
16/20
Instruction
4/20
Structured
9/15
Math
10/15
Multilingual
5/10
Reasoning: Adequate Coding: Strong Instruction Following: Poor Structured Output: Adequate Math: Adequate Multilingual: Adequate
ministral-3:8b
Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest