qwen3.8:latest
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
68 vs 85
Hardware Fit
22 vs 95
Quality Score
88 vs 81
Hardware
qwen3.8:latest gemma4:e4b-mlx
MachineSystem manufacturerMacBook Pro
CPUAMD Ryzen 9 5950X 16-Core ProcessorApple M2 Pro
Cores3210
RAM32 GB16 GB
GPUNVIDIA GeForce RTX 3090Apple M2 Pro
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.5
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3.8:latest gemma4:e4b-mlx
Tokens/sec10.047.3
First chunk1041 ms258 ms
TTFT14.3 s258 ms
Load time22.3 s5.1 s
Memory usage26.2 GB7.9 GB
Memory %82%49%
HW Fit Score Breakdown
qwen3.8:latest
Speed
12/50
TTFT
1/20
Memory
9/30
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
25/30
Quality
qwen3.8:latest
Reasoning
19/20
Coding
19/20
Instruction
10/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:e4b-mlx
Reasoning
15/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong 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