phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
qwen3.8-27b-uncensored-ymq-mtp
LM-STUDIO GGUFqwen35 · 27B
Sep 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor
Global Score
77 vs 84
Hardware Fit
74 vs 81
Quality Score
78 vs 85
Hardware
phi4:14b qwen3.8-27b-uncens…
MachineNVIDIA NVIDIA_DGX_SparkGigabyte Technology Co., Ltd. X570 AORUS PRO
CPUCortex-X925AMD Ryzen 5 5600X 6-Core Processor
Cores2012
RAM122 GB32 GB
GPUDevice 2e12NVIDIA GeForce RTX 5070 Ti
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformancebalanced
Performance
phi4:14b qwen3.8-27b-uncens…
Tokens/sec22.918.3
First chunk198 ms9 ms
TTFT198 ms522 ms
Load time10.3 s7.7 s
Memory usage14.7 GB14.9 GB
Memory %12%47%
HW Fit Score Breakdown
phi4:14b
Speed
24/50
TTFT
20/20
Memory
30/30
qwen3.8-27b-uncensored-…
Speed
35/50
TTFT
20/20
Memory
26/30
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
qwen3.8-27b-uncensored-…
Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
10/15
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