phi4-mini
OLLAMA GGUFAug 28, 2026 · Intel Core™ i5-10210U
qwopus3.6-27b-coder-compat-mtp
LM-STUDIO GGUFqwen35 · 27B · Q4_K_M
Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
51 vs 88
Hardware Fit
46 vs 80
Quality Score
53 vs 91
Hardware
phi4-mini qwopus3.6-27b-code…
MachineLENOVO 20U30029MBASUS
CPUIntel Core™ i5-10210UAMD Ryzen 7 7800X3D 8-Core Processor
Cores816
RAM15 GB31 GB
GPUCometLake-U GT2 [UHD Graphics]NVIDIA GeForce RTX 4090, Raphael
OSPop 24.04 LTScachyos rolling
Archx64x64
Power Modeperformanceperformance
Performance
phi4-mini qwopus3.6-27b-code…
Tokens/sec2.642.9
First chunk5406 ms32 ms
TTFT5.4 s413 ms
Load time27.4 sN/A
Memory usage4.6 GB24.6 GB
Memory %30%81%
HW Fit Score Breakdown
phi4-mini
Speed
6/50
TTFT
10/20
Memory
30/30
qwopus3.6-27b-coder-com…
Speed
50/50
TTFT
20/20
Memory
10/30
Quality
phi4-mini
Reasoning
11/20
Coding
9/20
Instruction
6/20
Structured
12/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong
qwopus3.6-27b-coder-com…
Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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