unsloth/gemma-4-26b-a4b-it
LM-STUDIO GGUFgemma4 · 26B · Q3_K_M
Apr 5, 2026 · Apple M4
nemotron-3-nano:latest
OLLAMA GGUFnemotron_h_moe · 31.6B · Q4_K_M
Mar 27, 2026 · AMD RYZEN AI MAX+ 395
Global Score
84 vs 89
Hardware Fit
64 vs 100
Quality Score
92 vs 84
Hardware
unsloth/gemma-4-26… nemotron-3-nano:la…
MachineMac miniAZW GTR Pro
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM24 GB125 GB
GPUApple M4Radeon 8060S
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
unsloth/gemma-4-26… nemotron-3-nano:la…
Tokens/sec16.565.2
First chunk32 ms295 ms
TTFT2.2 s295 ms
Load timeN/A8.7 s
Memory usage19.3 GB26.0 GB
Memory %80%21%
HW Fit Score Breakdown
unsloth/gemma-4-26b-a4b…
Speed
36/50
TTFT
18/20
Memory
10/30
nemotron-3-nano:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
unsloth/gemma-4-26b-a4b…
Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
nemotron-3-nano:latest
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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