phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Nov 4, 2026 · Intel Core™ i7-9700
qwen3-30b-a3b-t16-c32k-instruct:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 18, 2026 · Intel Xeon® E5-2637 v3
Global Score
75 vs 94
Hardware Fit
84 vs 100
Quality Score
71 vs 91
Hardware
phi4-mini:latest qwen3-30b-a3b-t16-…
MachineVMware, Inc. VMware Virtual PlatformDell Inc. Precision Tower 7910
CPUIntel Core™ i7-9700Intel Xeon® E5-2637 v3
Cores416
RAM16 GB96 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSUbuntu 24.04.5 LTSMicrosoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modeunknownbalanced
Performance
phi4-mini:latest qwen3-30b-a3b-t16-…
Tokens/sec10.8116.0
First chunk643 ms575 ms
TTFT643 ms575 ms
Load time31.5 s10.2 s
Memory usage2.9 GB21.0 GB
Memory %19%22%
HW Fit Score Breakdown
phi4-mini:latest
Speed
34/50
TTFT
20/20
Memory
30/30
qwen3-30b-a3b-t16-c32k-…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
phi4-mini:latest
Reasoning
13/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
qwen3-30b-a3b-t16-c32k-…
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
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