unsloth/gemma-4-26b-a4b-it
LM-STUDIO GGUFgemma4 · 26B · Q3_K_M
Apr 5, 2026 · Apple M4
rnj-1:8b
OLLAMA GGUFgemma3 · 8.3B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
84 vs 80
Hardware Fit
64 vs 93
Quality Score
92 vs 74
Hardware
unsloth/gemma-4-26… rnj-1:8b
MachineMac miniMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM24 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
unsloth/gemma-4-26… rnj-1:8b
Tokens/sec16.522.3
First chunk32 ms404 ms
TTFT2.2 s404 ms
Load timeN/A3.7 s
Memory usage19.3 GB8.3 GB
Memory %80%52%
HW Fit Score Breakdown
unsloth/gemma-4-26b-a4b…
Speed
36/50
TTFT
18/20
Memory
10/30
rnj-1:8b
Speed
49/50
TTFT
20/20
Memory
24/30
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
rnj-1:8b
Reasoning
12/20
Coding
19/20
Instruction
15/20
Structured
5/15
Math
14/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Weak 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