llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
gemma-4-26b-a4b-it@iq3_xxs
LM-STUDIO GGUFgemma4 · 26B · IQ3_XXS
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
72 vs 83
Hardware Fit
77 vs 58
Quality Score
70 vs 94
Hardware
llama3.1:8b gemma-4-26b-a4b-it…
MachineMacBook ProDocker Container
CPUApple M1 ProIntel Gen Intel® Core™ i9-11900H
Cores1016
RAM16 GB15 GB
GPUApple M1 ProTigerLake-H GT1 [UHD Graphics]
OSmacOS 26.6.2Ubuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance
Performance
llama3.1:8b gemma-4-26b-a4b-it…
Tokens/sec21.510.3
First chunk368 ms8 ms
TTFT368 ms3.5 s
Load time6.9 s10.9 s
Memory usage12.9 GB6.4 GB
Memory %81%41%
HW Fit Score Breakdown
llama3.1:8b
Speed
47/50
TTFT
20/20
Memory
10/30
gemma-4-26b-a4b-it@iq3_…
Speed
19/50
TTFT
12/20
Memory
27/30
Quality
llama3.1:8b
Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
gemma-4-26b-a4b-it@iq3_…
Reasoning
18/20
Coding
19/20
Instruction
19/20
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