gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
qwen3.5:35b
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
Global Score
81 vs 77
Hardware Fit
100 vs 53
Quality Score
73 vs 87
Hardware
gemma3n:latest qwen3.5:35b
MachineSupermicro AS -2015HS-TNRASUS
CPUAMD EPYC 9654P 96-Core ProcessorIntel Core™ i5-14600KF
Cores6420
RAM128 GB32 GB
GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]NVIDIA GeForce RTX 4070 Ti SUPER
OSUbuntu 24.04.3 LTSMicrosoft Windows 11 Famille 10.0.26200
Archx64x64
Power Modeperformancebalanced
Performance
gemma3n:latest qwen3.5:35b
Tokens/sec108.716.0
First chunk333 ms719 ms
TTFT333 ms719 ms
Load time4.5 s17.8 s
Memory usage8.6 GB25.0 GB
Memory %7%79%
HW Fit Score Breakdown
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5:35b
Speed
23/50
TTFT
20/20
Memory
10/30
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
qwen3.5:35b
Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
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