unsloth/gemma-4-26b-a4b-it
LM-STUDIO GGUFgemma4 · 26B · Q3_K_M
Apr 5, 2026 · Apple M4
stablelm2:1.6b
OLLAMA GGUFstablelm · 2B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
90 vs 45
Hardware Fit
85 vs 100
Quality Score
92 vs 22
Hardware
unsloth/gemma-4-26… stablelm2:1.6b
MachineMac miniMacBook Air
CPUApple M4Apple M4
Cores1010
RAM24 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
unsloth/gemma-4-26… stablelm2:1.6b
Tokens/sec24.993.8
First chunk15 msN/A
TTFT817 ms94 ms
Load timeN/A0.4 s
Memory usage16.8 GB1.1 GB
Memory %70%3%
HW Fit Score Breakdown
unsloth/gemma-4-26b-a4b…
Speed
50/50
TTFT
20/20
Memory
15/30
stablelm2:1.6b
Speed
40/50
TTFT
30/20
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
stablelm2:1.6b
Reasoning
4/20
Coding
7/20
Instruction
6/20
Structured
1/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
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