Back to leaderboard

phi4:14b

OLLAMA GGUF

phi3 · 14.7B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

qwen/qwen3-vl-30b

LM-STUDIO GGUF

qwen3vlmoe · 30B · Q4_K_M

Excellent

Apr 24, 2026 · AMD Ryzen 5 5500

Global Score
77 vs 92
Hardware Fit
74 vs 95
Quality Score
78 vs 90

Hardware

phi4:14b qwen/qwen3-vl-30b
MachineNVIDIA NVIDIA_DGX_SparkASUS
CPUCortex-X925AMD Ryzen 5 5500
Cores2012
RAM122 GB31 GB
GPUDevice 2e12Navi 44 [Radeon RX 9060 XT]
OSUbuntu 24.04.4 LTSNobara Linux 43
Archarm64x64
Power Modeperformanceperformance

Performance

phi4:14b qwen/qwen3-vl-30b
Tokens/sec22.924.8
First chunk198 ms11 ms
TTFT198 ms735 ms
Load time10.3 s11.7 s
Memory usage14.7 GB0.6 GB
Memory %12%2%

HW Fit Score Breakdown

phi4:14b

Speed
24/50
TTFT
20/20
Memory
30/30

qwen/qwen3-vl-30b

Speed
45/50
TTFT
20/20
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

qwen/qwen3-vl-30b

Reasoning
19/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View phi4:14b details | View qwen/qwen3-vl-30b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest