gemma4:e2b
OLLAMA GGUFgemma4 · 5.1B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Mar 5, 2026 · Apple M1 Max
Global Score
76 vs 62
Hardware Fit
82 vs 100
Quality Score
73 vs 46
Hardware
gemma4:e2b qwen3.5:0.8b
MachineLENOVO 20U30029MBMacBook Pro
CPUIntel Core™ i5-10210UApple M1 Max
Cores810
RAM15 GB32 GB
GPUCometLake-U GT2 [UHD Graphics]Apple M1 Max
OSPop 24.04 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced
Performance
gemma4:e2b qwen3.5:0.8b
Tokens/sec13.567.6
First chunk1270 ms209 ms
TTFT1.3 s209 ms
Load time13.4 s1.9 s
Memory usage6.5 GB2.6 GB
Memory %42%8%
HW Fit Score Breakdown
gemma4:e2b
Speed
35/50
TTFT
20/20
Memory
27/30
qwen3.5:0.8b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gemma4:e2b
Reasoning
10/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
qwen3.5:0.8b
Reasoning
9/20
Coding
4/20
Instruction
11/20
Structured
13/15
Math
3/15
Multilingual
6/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor 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