llama-3.1-8b-instruct
LM-STUDIO GGUFllama · 8B · Q8_0
Apr 26, 2026 · AMD Ryzen 5 5500
gemma-3-1b-it
LM-STUDIO GGUFgemma3 · 1B · Q4_K_M
Mar 5, 2026 · Intel Core™ i5-5300U
Global Score
81 vs 59
Hardware Fit
100 vs 76
Quality Score
73 vs 52
Hardware
llama-3.1-8b-instr… gemma-3-1b-it
MachineASUSLENOVO 20BUS00700
CPUAMD Ryzen 5 5500Intel Core™ i5-5300U
Cores124
RAM31 GB16 GB
GPUNavi 44 [Radeon RX 9060 XT]Intel(R) HD Graphics 5500
OSNobara Linux 43Microsoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modeperformancebalanced
Performance
llama-3.1-8b-instr… gemma-3-1b-it
Tokens/sec35.68.7
First chunk52 ms2078 ms
TTFT256 ms2.1 s
Load timeN/AN/A
Memory usage8.6 GB0.8 GB
Memory %28%5%
HW Fit Score Breakdown
llama-3.1-8b-instruct
Speed
50/50
TTFT
20/20
Memory
30/30
gemma-3-1b-it
Speed
29/50
TTFT
19/20
Memory
28/30
Quality
llama-3.1-8b-instruct
Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
gemma-3-1b-it
Reasoning
4/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor 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