qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
gemma4:26b-nvfp4
OLLAMA GGUFnvfp4
May 25, 2026 · Apple M4 Pro
Global Score
84 vs 85
Hardware Fit
97 vs 80
Quality Score
79 vs 87
Hardware
qwen3:8b gemma4:26b-nvfp4
MachineASUSMacBook Pro
CPUIntel Core™ Ultra 9 285KApple M4 Pro
Cores2414
RAM47 GB48 GB
GPUNVIDIA GeForce RTX 5090, Intel(R) GraphicsApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.4.1
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3:8b gemma4:26b-nvfp4
Tokens/sec208.065.7
First chunk82 ms233 ms
TTFT1.3 s30.0 s
Load time1.5 s5.0 s
Memory usage9.6 GB15.2 GB
Memory %20%32%
HW Fit Score Breakdown
qwen3:8b
Speed
50/50
TTFT
18/20
Memory
29/30
gemma4:26b-nvfp4
Speed
50/50
TTFT
0/20
Memory
30/30
Quality
qwen3:8b
Reasoning
18/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:26b-nvfp4
Reasoning
17/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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