google/gemma-4-e4b
LM-STUDIO GGUFgemma4 · Q4_K_M
Jul 7, 2026 · AMD Ryzen 7 5800H
hf.co/openbmb/MiniCPM5-1B-GGUF:F16
OLLAMA GGUFllama · 1.08B · F16
Aug 23, 2026 · Apple M1 Pro
Global Score
62 vs 62
Hardware Fit
77 vs 100
Quality Score
55 vs 45
Hardware
google/gemma-4-e4b hf.co/openbmb/Mini…
MachineLENOVO 82JQMacBook Pro
CPUAMD Ryzen 7 5800HApple M1 Pro
Cores1610
RAM16 GB16 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUApple M1 Pro
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
google/gemma-4-e4b hf.co/openbmb/Mini…
Tokens/sec27.688.0
First chunk23 ms36 ms
TTFT480 ms36 ms
Load timeN/A1.6 s
Memory usage13.2 GB3.9 GB
Memory %83%25%
HW Fit Score Breakdown
google/gemma-4-e4b
Speed
48/50
TTFT
20/20
Memory
9/30
hf.co/openbmb/MiniCPM5-…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
google/gemma-4-e4b
Reasoning
18/20
Coding
17/20
Instruction
5/20
Structured
3/15
Math
11/15
Multilingual
1/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
hf.co/openbmb/MiniCPM5-…
Reasoning
16/20
Coding
9/20
Instruction
4/20
Structured
0/15
Math
14/15
Multilingual
2/10
Reasoning: Strong Coding: Weak Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor
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