Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

qwen3.6:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Excellent

Apr 23, 2026 · AMD RYZEN AI MAX+ 395

Global Score
70 vs 80
Hardware Fit
73 vs 60
Quality Score
68 vs 89

Hardware

llama3.1:8b-instru… qwen3.6:27b
Machine—AZW GTR Pro
CPUC1-ProAMD RYZEN AI MAX+ 395
Cores032
RAM11 GB125 GB
GPUIntegrated / UnknownRadeon 8060S
OSunknown unknownUbuntu 24.04.4 LTS
Archarm64x64
Power Modeunknownlow-power

Performance

llama3.1:8b-instru… qwen3.6:27b
Tokens/sec6.511.2
First chunk950 ms429 ms
TTFT950 ms429 ms
Load time11.5 s8.8 s
Memory usage4.4 GB39.7 GB
Memory %38%32%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

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

qwen3.6:27b

Speed
10/50
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

qwen3.6:27b

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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