qwen3.5-9b-mlx
LM-STUDIO MLXqwen3_5 · 9B · 4bit
Mar 11, 2026 · Apple M4
smollm2:135m
OLLAMA GGUFllama · 134.52M · F16
Mar 2, 2026 · Apple M4
Global Score
58 vs 41
Hardware Fit
68 vs 100
Quality Score
54 vs 15
Hardware
qwen3.5-9b-mlx smollm2:135m
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-9b-mlx smollm2:135m
Tokens/sec16.7241.0
First chunk23 msN/A
TTFT14.1 s39 ms
Load timeN/A0.4 s
Memory usage7.8 GB0.6 GB
Memory %33%2%
HW Fit Score Breakdown
qwen3.5-9b-mlx
Speed
36/50
TTFT
3/20
Memory
29/30
smollm2:135m
Speed
40/50
TTFT
30/20
Memory
30/30
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
smollm2:135m
Reasoning
4/20
Coding
1/20
Instruction
6/20
Structured
2/15
Math
1/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
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