lmstudio-community/Phi-4-reasoning-plus-MLX-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
qwen3.5:35b-a3b-q4_K_M
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Jul 30, 2026 · Intel Xeon® E5-2637 v3
Global Score
33 vs 49
Hardware Fit
74 vs 54
Quality Score
15 vs 47
Hardware
lmstudio-community… qwen3.5:35b-a3b-q4…
MachineMacBook AirDell Inc. Precision Tower 7910
CPUApple M4Intel Xeon® E5-2637 v3
Cores1016
RAM32 GB96 GB
GPUApple M4NVIDIA GeForce RTX 5060 Ti
OSmacOS 26.3Microsoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
lmstudio-community… qwen3.5:35b-a3b-q4…
Tokens/sec11.521.6
First chunk670 ms1505 ms
TTFT670 ms30.0 s
Load timeN/A53.8 s
Memory usage3.0 GB22.7 GB
Memory %9%24%
HW Fit Score Breakdown
lmstudio-community/Phi-…
Speed
24/50
TTFT
20/20
Memory
30/30
qwen3.5:35b-a3b-q4_K_M
Speed
24/50
TTFT
0/20
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
qwen3.5:35b-a3b-q4_K_M
Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
5/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate 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