gemma4:e2b
OLLAMA GGUFgemma4 · 5.1B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Mar 2, 2026 · Apple M4
Global Score
72 vs 65
Hardware Fit
71 vs 99
Quality Score
72 vs 51
Hardware
gemma4:e2b qwen3.5:0.8b
MachineDell Inc. Inspiron 15 3530MacBook Air
CPUIntel Gen Intel® Core™ i7-1355UApple M4
Cores1210
RAM31 GB32 GB
GPURaptor Lake-P [Iris Xe Graphics]Apple M4
OScachyos rollingmacOS 26.3
Archx64arm64
Power Modelow-powerbalanced
Performance
gemma4:e2b qwen3.5:0.8b
Tokens/sec10.848.2
First chunk1408 msN/A
TTFT1.4 s195 ms
Load time6.0 s1.0 s
Memory usage7.2 GB2.5 GB
Memory %23%8%
HW Fit Score Breakdown
gemma4:e2b
Speed
21/50
TTFT
20/20
Memory
30/30
qwen3.5:0.8b
Speed
40/50
TTFT
30/20
Memory
29/30
Quality
gemma4:e2b
Reasoning
10/20
Coding
16/20
Instruction
14/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
qwen3.5:0.8b
Reasoning
9/20
Coding
6/20
Instruction
11/20
Structured
13/15
Math
5/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
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