microsoft/phi-4-mini-reasoning
LM-STUDIO MLXphi3 · 3.8B · 4bit
Mar 3, 2026 · Apple M4
huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp
LM-STUDIO GGUFqwen35moe · 35B · Q4_K
Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
62 vs 88
Hardware Fit
99 vs 94
Quality Score
46 vs 85
Hardware
microsoft/phi-4-mi… huihui-qwen3.6-35b…
MachineMacBook AirGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUApple M4AMD Ryzen 5 5600X 6-Core Processor
Cores1012
RAM32 GB47 GB
GPUApple M4AD106 [GeForce RTX 4060 Ti]
OSmacOS 26.3cachyos rolling
Archarm64x64
Power Modebalancedlow-power
Performance
microsoft/phi-4-mi… huihui-qwen3.6-35b…
Tokens/sec40.339.8
First chunk289 ms3 ms
TTFT289 ms479 ms
Load timeN/AN/A
Memory usage2.0 GB24.4 GB
Memory %6%52%
HW Fit Score Breakdown
microsoft/phi-4-mini-re…
Speed
50/50
TTFT
20/20
Memory
29/30
huihui-qwen3.6-35b-a3b-…
Speed
50/50
TTFT
20/20
Memory
24/30
Quality
microsoft/phi-4-mini-re…
Reasoning
7/20
Coding
6/20
Instruction
7/20
Structured
7/15
Math
12/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Adequate
huihui-qwen3.6-35b-a3b-…
Reasoning
18/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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