llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
gemma4:26b-nvfp4
OLLAMA GGUFnvfp4
May 25, 2026 · Apple M4 Pro
Global Score
46 vs 85
Hardware Fit
61 vs 80
Quality Score
40 vs 87
Hardware
llama3.1:8b gemma4:26b-nvfp4
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMacBook Pro
CPUCortex-A78AEApple M4 Pro
Cores614
RAM7 GB48 GB
GPUIntegrated / UnknownApple M4 Pro
OSUbuntu 22.04.5 LTSmacOS 26.4.1
Archarm64arm64
Power Modebalancedbalanced
Performance
llama3.1:8b gemma4:26b-nvfp4
Tokens/sec7.865.7
First chunk1625 ms233 ms
TTFT1.6 s30.0 s
Load time21.8 s5.0 s
Memory usage5.2 GB15.2 GB
Memory %71%32%
HW Fit Score Breakdown
llama3.1:8b
Speed
26/50
TTFT
20/20
Memory
15/30
gemma4:26b-nvfp4
Speed
50/50
TTFT
0/20
Memory
30/30
Quality
llama3.1:8b
Reasoning
12/20
Coding
10/20
Instruction
4/20
Structured
1/15
Math
4/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Poor Structured Output: Poor Math: Weak 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