lmstudio-community/Phi-4-reasoning-plus-MLX-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
qwen3.6:35b-a3b-q8_0
OLLAMA GGUFqwen35moe · 36.0B · Q8_0
Jul 7, 2026 · Cortex-X925
Global Score
33 vs 80
Hardware Fit
74 vs 79
Quality Score
15 vs 81
Hardware
lmstudio-community… qwen3.6:35b-a3b-q8_0
MachineMacBook AirASUSTeK COMPUTER INC. GX10
CPUApple M4Cortex-X925
Cores1020
RAM32 GB122 GB
GPUApple M4Device 2e12
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
lmstudio-community… qwen3.6:35b-a3b-q8_0
Tokens/sec11.555.5
First chunk670 ms528 ms
TTFT670 ms30.0 s
Load timeN/A32.6 s
Memory usage3.0 GB41.0 GB
Memory %9%34%
HW Fit Score Breakdown
lmstudio-community/Phi-…
Speed
24/50
TTFT
20/20
Memory
30/30
qwen3.6:35b-a3b-q8_0
Speed
50/50
TTFT
0/20
Memory
29/30
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
qwen3.6:35b-a3b-q8_0
Reasoning
18/20
Coding
13/20
Instruction
17/20
Structured
10/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Adequate 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