lmstudio-community/Phi-4-reasoning-plus-MLX-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
qwen3.5-2b-mlx
LM-STUDIO MLXqwen3_5 · 2B · 8bit
Mar 3, 2026 · Apple M4
Global Score
33 vs 70
Hardware Fit
74 vs 93
Quality Score
15 vs 60
Hardware
lmstudio-community… qwen3.5-2b-mlx
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
lmstudio-community… qwen3.5-2b-mlx
Tokens/sec11.532.9
First chunk670 ms3096 ms
TTFT670 ms3.1 s
Load timeN/AN/A
Memory usage3.0 GB2.5 GB
Memory %9%8%
HW Fit Score Breakdown
lmstudio-community/Phi-…
Speed
24/50
TTFT
20/20
Memory
30/30
qwen3.5-2b-mlx
Speed
50/50
TTFT
13/20
Memory
30/30
Quality
lmstudio-community/Phi-…
Reasoning
8/20
Coding
1/20
Instruction
1/20
Structured
1/15
Math
1/15
Multilingual
3/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Weak
qwen3.5-2b-mlx
Reasoning
11/20
Coding
9/20
Instruction
14/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Weak 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