phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
qwen3.5:35b-a3b-q4_K_M
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Jul 31, 2026 · Intel Xeon® E5-2637 v3
Global Score
77 vs 81
Hardware Fit
74 vs 72
Quality Score
78 vs 85
Hardware
phi4:14b qwen3.5:35b-a3b-q4…
MachineNVIDIA NVIDIA_DGX_SparkDell Inc. Precision Tower 7910
CPUCortex-X925Intel Xeon® E5-2637 v3
Cores2016
RAM122 GB96 GB
GPUDevice 2e12NVIDIA GeForce RTX 5060 Ti
OSUbuntu 24.04.4 LTSMicrosoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modeperformancebalanced
Performance
phi4:14b qwen3.5:35b-a3b-q4…
Tokens/sec22.924.2
First chunk198 ms1607 ms
TTFT198 ms1.6 s
Load time10.3 s66.4 s
Memory usage14.7 GB22.7 GB
Memory %12%24%
HW Fit Score Breakdown
phi4:14b
Speed
24/50
TTFT
20/20
Memory
30/30
qwen3.5:35b-a3b-q4_K_M
Speed
28/50
TTFT
14/20
Memory
30/30
Quality
phi4:14b
Reasoning
18/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
qwen3.5:35b-a3b-q4_K_M
Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong 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