qwen3-coder:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
76 vs 78
Hardware Fit
51 vs 47
Quality Score
87 vs 92
Hardware
qwen3-coder:latest gemma4:31b
MachineDell Inc. Inspiron 15 3530AZW GTR Pro
CPUIntel Gen Intel® Core™ i7-1355UAMD RYZEN AI MAX+ 395
Cores1232
RAM31 GB125 GB
GPURaptor Lake-P [Iris Xe Graphics]Radeon 8060S
OScachyos rollingUbuntu 24.04.4 LTS
Archx64x64
Power Modelow-powerperformance
Performance
qwen3-coder:latest gemma4:31b
Tokens/sec7.69.8
First chunk2037 ms873 ms
TTFT2.0 s873 ms
Load time8.7 s7.0 s
Memory usage18.9 GB68.3 GB
Memory %61%55%
HW Fit Score Breakdown
qwen3-coder:latest
Speed
13/50
TTFT
18/20
Memory
20/30
gemma4:31b
Speed
8/50
TTFT
16/20
Memory
23/30
Quality
qwen3-coder:latest
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
gemma4:31b
Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
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