hf.co/unsloth/gemma-4-E2B-it-GGUF:UD-Q8_K_XL
OLLAMA GGUFgemma4 · 4.65B · unknown
Aug 23, 2026 · Apple M1 Pro
Qwen3-30B:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
84 vs 88
Hardware Fit
99 vs 91
Quality Score
77 vs 87
Hardware
hf.co/unsloth/gemm… Qwen3-30B:30b
MachineMacBook ProHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUApple M1 ProAMD Ryzen 9 9955HX3D 16-Core Processor
Cores1032
RAM16 GB31 GB
GPUApple M1 ProAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSmacOS 26.6.2Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
hf.co/unsloth/gemm… Qwen3-30B:30b
Tokens/sec48.042.5
First chunk167 ms442 ms
TTFT167 ms442 ms
Load time4.7 s21.7 s
Memory usage5.3 GB17.9 GB
Memory %33%58%
HW Fit Score Breakdown
hf.co/unsloth/gemma-4-E…
Speed
50/50
TTFT
20/20
Memory
29/30
Qwen3-30B:30b
Speed
50/50
TTFT
20/20
Memory
21/30
Quality
hf.co/unsloth/gemma-4-E…
Reasoning
12/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
Qwen3-30B:30b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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