qwen3.5-0.8b
LM-STUDIO GGUFqwen35 · 0.8B · Q4_K_M
Mar 6, 2026 · Intel Core™ i5-5300U
gemma3:4b
OLLAMA GGUFgemma3 · 4.3B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
48 vs 76
Hardware Fit
61 vs 92
Quality Score
42 vs 69
Hardware
qwen3.5-0.8b gemma3:4b
MachineLENOVO 20BUS00700NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUIntel Core™ i5-5300UCortex-A78AE
Cores46
RAM16 GB7 GB
GPUIntel(R) HD Graphics 5500Integrated / Unknown
OSMicrosoft Windows 10 Professionnel 10.0.19045Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced
Performance
qwen3.5-0.8b gemma3:4b
Tokens/sec6.215.0
First chunk4461 ms2380 ms
TTFT4.5 s2.4 s
Load timeN/A13.6 s
Memory usage0.7 GB2.6 GB
Memory %4%35%
HW Fit Score Breakdown
qwen3.5-0.8b
Speed
22/50
TTFT
12/20
Memory
27/30
gemma3:4b
Speed
45/50
TTFT
18/20
Memory
29/30
Quality
qwen3.5-0.8b
Reasoning
10/20
Coding
2/20
Instruction
10/20
Structured
12/15
Math
2/15
Multilingual
6/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
gemma3:4b
Reasoning
11/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong 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