qwen3.5:9b-mlx
OLLAMA GGUFnvfp4
Aug 26, 2026 · Apple M1 Pro
qwen2.5:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
54 vs 84
Hardware Fit
81 vs 95
Quality Score
43 vs 79
Hardware
qwen3.5:9b-mlx qwen2.5:7b
MachineMacBook ProMacBook Air
CPUApple M1 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M1 ProApple M4
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5:9b-mlx qwen2.5:7b
Tokens/sec25.222.2
First chunk341 msN/A
TTFT6.3 s285 ms
Load time3.4 s0.8 s
Memory usage8.4 GB7.6 GB
Memory %52%24%
HW Fit Score Breakdown
qwen3.5:9b-mlx
Speed
50/50
TTFT
7/20
Memory
24/30
qwen2.5:7b
Speed
35/50
TTFT
30/20
Memory
30/30
Quality
qwen3.5:9b-mlx
Reasoning
14/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong
qwen2.5:7b
Reasoning
14/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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