qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 31, 2026 · Intel Xeon® E5-4620 0
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
71 vs 84
Hardware Fit
42 vs 82
Quality Score
84 vs 85
Hardware
qwen3:30b-a3b-inst… gemma4:12b-mlx
MachineDell Inc. PowerEdge R820MacBook Pro
CPUIntel Xeon® E5-4620 0Apple M2 Pro
Cores6410
RAM256 GB16 GB
GPUMicrosoft Remote Display Adapter, Microsoft Basic Display AdapterApple M2 Pro
OSMicrosoft Windows Server 2022 Datacenter 10.0.20348macOS 26.5
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3:30b-a3b-inst… gemma4:12b-mlx
Tokens/sec4.027.2
First chunk2070 ms732 ms
TTFT2.1 s8.1 s
Load time44.5 s3.5 s
Memory usage17.7 GB7.1 GB
Memory %7%44%
HW Fit Score Breakdown
qwen3:30b-a3b-instruct-…
Speed
3/50
TTFT
9/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
Quality
qwen3:30b-a3b-instruct-…
Reasoning
18/20
Coding
18/20
Instruction
11/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:12b-mlx
Reasoning
16/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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