gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-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
81 vs 95
Hardware Fit
100 vs 94
Quality Score
73 vs 96
Hardware
gemma3n:latest qwen3-30b-a3b-thin…
MachineSupermicro AS -2015HS-TNRMac Studio
CPUAMD EPYC 9654P 96-Core ProcessorApple M2 Max
Cores6412
RAM128 GB96 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]Apple M2 Max
OSUbuntu 24.04.3 LTSmacOS 26.1
Archx64arm64
Power Modeperformancebalanced
Performance
gemma3n:latest qwen3-30b-a3b-thin…
Tokens/sec108.780.4
First chunk333 ms46 ms
TTFT333 ms1.8 s
Load time4.5 sN/A
Memory usage8.6 GB21.2 GB
Memory %7%22%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
Quality
gemma3n:latest
Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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