gemma4:e4b-it-q8_0
OLLAMA GGUFgemma4 · 8.0B · Q8_0
Aug 26, 2026 · Apple M1 Pro
gpt-oss-orchestrator:latest
OLLAMA GGUFgptoss · 20.9B · MXFP4
Mar 19, 2026 · Apple M4
Global Score
91 vs 88
Hardware Fit
88 vs 80
Quality Score
92 vs 91
Hardware
gemma4:e4b-it-q8_0 gpt-oss-orchestrat…
MachineMacBook ProMac mini
CPUApple M1 ProApple M4
Cores1010
RAM16 GB24 GB
GPUApple M1 ProApple M4
OSmacOS 26.6.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:e4b-it-q8_0 gpt-oss-orchestrat…
Tokens/sec30.024.6
First chunk311 ms525 ms
TTFT6.2 s4.8 s
Load time6.9 s8.5 s
Memory usage5.0 GB13.8 GB
Memory %31%58%
HW Fit Score Breakdown
gemma4:e4b-it-q8_0
Speed
50/50
TTFT
8/20
Memory
30/30
gpt-oss-orchestrator:la…
Speed
49/50
TTFT
10/20
Memory
21/30
Quality
gemma4:e4b-it-q8_0
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gpt-oss-orchestrator:la…
Reasoning
19/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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