llama3.2:3b
OLLAMA GGUFllama · 3.2B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
Global Score
67 vs 81
Hardware Fit
77 vs 100
Quality Score
63 vs 73
Hardware
llama3.2:3b gemma3n:latest
MachineLENOVO 20U30029MBSupermicro AS -2015HS-TNR
CPUIntel Core™ i5-10210UAMD EPYC 9654P 96-Core Processor
Cores864
RAM15 GB128 GB
GPUCometLake-U GT2 [UHD Graphics]GH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSPop 24.04 LTSUbuntu 24.04.3 LTS
Archx64x64
Power Modelow-powerperformance
Performance
llama3.2:3b gemma3n:latest
Tokens/sec10.0108.7
First chunk1166 ms333 ms
TTFT1.2 s333 ms
Load time6.8 s4.5 s
Memory usage3.8 GB8.6 GB
Memory %25%7%
HW Fit Score Breakdown
llama3.2:3b
Speed
27/50
TTFT
20/20
Memory
30/30
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
llama3.2:3b
Reasoning
11/20
Coding
15/20
Instruction
13/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
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
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