Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Oct 11, 2026 · AMD Ryzen 5 5500

Global Score
70 vs 74
Hardware Fit
73 vs 100
Quality Score
68 vs 63

Hardware

llama3.1:8b-instru… qwen3:0.6b
Machine—Microsoft WSL
CPUC1-ProAMD Ryzen 5 5500
Cores012
RAM11 GB8 GB
GPUIntegrated / UnknownIntegrated / Unknown
OSunknown unknownUbuntu 26.04.1 LTS
Archarm64x64
Power Modeunknownunknown

Performance

llama3.1:8b-instru… qwen3:0.6b
Tokens/sec6.5249.5
First chunk950 ms80 ms
TTFT950 ms659 ms
Load time11.5 s6.3 s
Memory usage4.4 GB0.9 GB
Memory %38%11%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

Speed
25/50
TTFT
20/20
Memory
28/30

qwen3:0.6b

Speed
50/50
TTFT
20/20
Memory
30/30

Quality

llama3.1:8b-instruct-q4…

Reasoning
11/20
Coding
17/20
Instruction
11/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen3:0.6b

Reasoning
13/20
Coding
6/20
Instruction
12/20
Structured
13/15
Math
12/15
Multilingual
7/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Adequate

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest