qwen3.5:0.8b
OLLAMA GGUFqwen35 · 873.44M · Q8_0
Apr 29, 2026 · Intel Core™ i5-8350U
gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
Global Score
18 vs 81
Hardware Fit
53 vs 100
Quality Score
3 vs 73
Hardware
qwen3.5:0.8b gemma3n:latest
MachineLENOVO 20L7CTO1WWSupermicro AS -2015HS-TNR
CPUIntel Core™ i5-8350UAMD EPYC 9654P 96-Core Processor
Cores864
RAM23 GB128 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]GH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSFedora Linux 43Ubuntu 24.04.3 LTS
Archx64x64
Power Modelow-powerperformance
Performance
qwen3.5:0.8b gemma3n:latest
Tokens/sec9.4108.7
First chunk799 ms333 ms
TTFT30.0 s333 ms
Load time3.3 s4.5 s
Memory usage1.9 GB8.6 GB
Memory %8%7%
HW Fit Score Breakdown
qwen3.5:0.8b
Speed
23/50
TTFT
0/20
Memory
30/30
gemma3n:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
qwen3.5:0.8b
Reasoning
0/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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