qwen3.5-9b-mlx
LM-STUDIO MLXqwen3_5 · 9B · 4bit
Mar 12, 2026 · Apple M4 Pro
llama3.2:latest
OLLAMA GGUFllama · 3.2B · Q4_K_M
Feb 28, 2026 · Apple M4 Pro
Global Score
77 vs 73
Hardware Fit
67 vs 100
Quality Score
81 vs 61
Hardware
qwen3.5-9b-mlx llama3.2:latest
MachineMac miniMac Mini
CPUApple M4 ProApple M4 Pro
Cores1414
RAM64 GB64 GB
GPUApple M4 ProApple M4 Pro
OSmacOS 15.7.4macOS 15.7.4
Archarm64arm64
Power Modebalancedunknown
Performance
qwen3.5-9b-mlx llama3.2:latest
Tokens/sec20.398.9
First chunk4216 msN/A
TTFT4.2 s125 ms
Load timeN/A2.3 s
Memory usage5.6 GB22.1 GB
Memory %9%35%
HW Fit Score Breakdown
qwen3.5-9b-mlx
Speed
29/50
TTFT
8/20
Memory
30/30
llama3.2:latest
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
qwen3.5-9b-mlx
Reasoning
15/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
llama3.2:latest
Reasoning
11/20
Coding
14/20
Instruction
12/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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