gemma-4-e2b-it-qat
LM-STUDIO GGUFgemma4 · Q4_K_XL
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
Global Score
81 vs 83
Hardware Fit
90 vs 100
Quality Score
77 vs 76
Hardware
gemma-4-e2b-it-qat qwen3.5:4b
MachineDocker ContainerMacBook Pro
CPUIntel Gen Intel® Core™ i9-11900HApple M1 Max
Cores1610
RAM15 GB32 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M1 Max
OSUbuntu 26.04 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
gemma-4-e2b-it-qat qwen3.5:4b
Tokens/sec22.232.4
First chunk67 ms306 ms
TTFT1.1 s306 ms
Load time5.4 s2.7 s
Memory usage0.0 GB6.5 GB
Memory %0%20%
HW Fit Score Breakdown
gemma-4-e2b-it-qat
Speed
40/50
TTFT
20/20
Memory
30/30
qwen3.5:4b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gemma-4-e2b-it-qat
Reasoning
10/20
Coding
17/20
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
qwen3.5:4b
Reasoning
16/20
Coding
14/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak 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