Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Good

Mar 7, 2026 · AMD Ryzen 5 5500

Global Score
70 vs 71
Hardware Fit
73 vs 56
Quality Score
68 vs 78

Hardware

llama3.1:8b-instru… qwen3.5:9b
Machine—System manufacturer
CPUC1-ProAMD Ryzen 5 5500
Cores012
RAM11 GB16 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 3060
OSunknown unknownMicrosoft Windows 11 IoT Enterprise LTSC 10.0.26100
Archarm64x64
Power Modeunknownbalanced

Performance

llama3.1:8b-instru… qwen3.5:9b
Tokens/sec6.55.3
First chunk950 ms1624 ms
TTFT950 ms1.6 s
Load time11.5 s4.0 s
Memory usage4.4 GB7.9 GB
Memory %38%50%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

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

qwen3.5:9b

Speed
11/50
TTFT
20/20
Memory
25/30

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

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
12/20
Structured
15/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

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