Back to leaderboard

phi4:14b

OLLAMA GGUF

phi3 · 14.7B · Q4_K_M

Good

Jun 26, 2026 · Cortex-X925

qwen3-0.6b

LM-STUDIO GGUF

qwen3 · 0.6B · Q4_K_M

Marginal

Mar 5, 2026 · Intel Core™ i5-5300U

Global Score
77 vs 40
Hardware Fit
74 vs 89
Quality Score
78 vs 19

Hardware

phi4:14b qwen3-0.6b
MachineNVIDIA NVIDIA_DGX_SparkLENOVO 20BUS00700
CPUCortex-X925Intel Core™ i5-5300U
Cores204
RAM122 GB16 GB
GPUDevice 2e12Intel(R) HD Graphics 5500
OSUbuntu 24.04.4 LTSMicrosoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modeperformancebalanced

Performance

phi4:14b qwen3-0.6b
Tokens/sec22.914.4
First chunk198 ms854 ms
TTFT198 ms854 ms
Load time10.3 sN/A
Memory usage14.7 GB0.5 GB
Memory %12%3%

HW Fit Score Breakdown

phi4:14b

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

qwen3-0.6b

Speed
43/50
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

qwen3-0.6b

Reasoning
5/20
Coding
1/20
Instruction
3/20
Structured
4/15
Math
0/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Poor Multilingual: Adequate

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