lmstudio-community/Phi-4-reasoning-plus-MLX-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 6bit
Jul 17, 2026 · Apple M5 Max
Global Score
33 vs 87
Hardware Fit
74 vs 90
Quality Score
15 vs 86
Hardware
lmstudio-community… qwen/qwen3.6-35b-a3b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M5 Max
Cores1018
RAM32 GB64 GB
GPUApple M4Apple M5 Max
OSmacOS 26.3macOS 27.0
Archarm64arm64
Power Modebalancedbalanced
Performance
lmstudio-community… qwen/qwen3.6-35b-a3b
Tokens/sec11.586.5
First chunk670 ms9 ms
TTFT670 ms175 ms
Load timeN/AN/A
Memory usage3.0 GB37.9 GB
Memory %9%59%
HW Fit Score Breakdown
lmstudio-community/Phi-…
Speed
24/50
TTFT
20/20
Memory
30/30
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
20/30
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
qwen/qwen3.6-35b-a3b
Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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