gemma4:e4b-it-q8_0
OLLAMA GGUFgemma4 · 8.0B · Q8_0
Aug 25, 2026 · Apple M1 Pro
qwen3.5:27b
OLLAMA GGUFqwen35 · 27.8B · Q4_K_M
Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Global Score
88 vs 79
Hardware Fit
100 vs 57
Quality Score
83 vs 89
Hardware
gemma4:e4b-it-q8_0 qwen3.5:27b
MachineMacBook ProAZW GTR Pro
CPUApple M1 ProAMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Cores1032
RAM16 GB125 GB
GPUApple M1 ProIntegrated / Apple Silicon
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance
Performance
gemma4:e4b-it-q8_0 qwen3.5:27b
Tokens/sec27.810.7
First chunk204 ms341 ms
TTFT204 ms341 ms
Load time6.6 s10.2 s
Memory usage5.0 GB39.7 GB
Memory %31%32%
HW Fit Score Breakdown
gemma4:e4b-it-q8_0
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5:27b
Speed
9/50
TTFT
20/20
Memory
28/30
Quality
gemma4:e4b-it-q8_0
Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
qwen3.5:27b
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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