unsloth/gemma-4-26b-a4b-it
LM-STUDIO GGUFgemma4 · 26B · Q3_K_M
Apr 5, 2026 · Apple M4
llama-3.1-8b-instruct
LM-STUDIO GGUFllama · 8B · Q8_0
Apr 26, 2026 · AMD Ryzen 5 5500
Global Score
84 vs 81
Hardware Fit
64 vs 100
Quality Score
92 vs 73
Hardware
unsloth/gemma-4-26… llama-3.1-8b-instr…
MachineMac miniASUS
CPUApple M4AMD Ryzen 5 5500
Cores1012
RAM24 GB31 GB
GPUApple M4Navi 44 [Radeon RX 9060 XT]
OSmacOS 26.3Nobara Linux 43
Archarm64x64
Power Modebalancedperformance
Performance
unsloth/gemma-4-26… llama-3.1-8b-instr…
Tokens/sec16.535.6
First chunk32 ms52 ms
TTFT2.2 s256 ms
Load timeN/AN/A
Memory usage19.3 GB8.6 GB
Memory %80%28%
HW Fit Score Breakdown
unsloth/gemma-4-26b-a4b…
Speed
36/50
TTFT
18/20
Memory
10/30
llama-3.1-8b-instruct
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
llama-3.1-8b-instruct
Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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