gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · Apple M4
Qwen3-Coder-30B:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 18, 2026 · Intel Core™ i7-14700F
Global Score
33 vs 91
Hardware Fit
50 vs 100
Quality Score
25 vs 87
Hardware
gemma4:26b Qwen3-Coder-30B:30b
MachineMac miniHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUApple M4Intel Core™ i7-14700F
Cores1028
RAM24 GB128 GB
GPUApple M4NVIDIA GeForce RTX 5080
OSmacOS 26.3Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:26b Qwen3-Coder-30B:30b
Tokens/sec20.074.0
First chunk941 ms381 ms
TTFT30.0 s381 ms
Load time0.2 s15.3 s
Memory usage20.3 GB17.9 GB
Memory %85%14%
HW Fit Score Breakdown
gemma4:26b
Speed
42/50
TTFT
0/20
Memory
8/30
Qwen3-Coder-30B:30b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gemma4:26b
Reasoning
14/20
Coding
1/20
Instruction
6/20
Structured
3/15
Math
0/15
Multilingual
1/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
Qwen3-Coder-30B:30b
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
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