gemma4:31b
OLLAMA GGUFgemma4 · 30.7B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 22, 2026 · Apple M2 Max
Global Score
64 vs 95
Hardware Fit
41 vs 94
Quality Score
74 vs 96
Hardware
gemma4:31b qwen3-30b-a3b-thin…
MachineSystem manufacturerMac Studio
CPUAMD Ryzen 9 5950X 16-Core ProcessorApple M2 Max
Cores3212
RAM32 GB96 GB
GPUNVIDIA GeForce RTX 3090Apple M2 Max
OSMicrosoft Windows 11 Pro 10.0.26300macOS 26.1
Archx64arm64
Power Modebalancedbalanced
Performance
gemma4:31b qwen3-30b-a3b-thin…
Tokens/sec9.580.4
First chunk1751 ms46 ms
TTFT30.0 s1.8 s
Load time33.9 sN/A
Memory usage1.4 GB21.2 GB
Memory %4%22%
HW Fit Score Breakdown
gemma4:31b
Speed
11/50
TTFT
0/20
Memory
30/30
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
Quality
gemma4:31b
Reasoning
11/20
Coding
17/20
Instruction
10/20
Structured
15/15
Math
12/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
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