gemma4:e2b
OLLAMA GGUFgemma4 · 5.1B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
qwen3.5:4b-mlx
OLLAMA GGUFnvfp4
Aug 25, 2026 · Apple M1 Pro
Global Score
76 vs 68
Hardware Fit
82 vs 91
Quality Score
73 vs 58
Hardware
gemma4:e2b qwen3.5:4b-mlx
MachineLENOVO 20U30029MBMacBook Pro
CPUIntel Core™ i5-10210UApple M1 Pro
Cores810
RAM15 GB16 GB
GPUCometLake-U GT2 [UHD Graphics]Apple M1 Pro
OSPop 24.04 LTSmacOS 26.6.2
Archx64arm64
Power Modeperformancebalanced
Performance
gemma4:e2b qwen3.5:4b-mlx
Tokens/sec13.542.2
First chunk1270 ms201 ms
TTFT1.3 s4.4 s
Load time13.4 s0.0 s
Memory usage6.5 GB3.8 GB
Memory %42%24%
HW Fit Score Breakdown
gemma4:e2b
Speed
35/50
TTFT
20/20
Memory
27/30
qwen3.5:4b-mlx
Speed
50/50
TTFT
11/20
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
qwen3.5:4b-mlx
Reasoning
16/20
Coding
2/20
Instruction
13/20
Structured
7/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate 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