Back to leaderboard

llama3.1:8b-instruct-q4_K_S

OLLAMA GGUF

llama · 8.0B · Q4_K_S

Good

Nov 22, 2026 · C1-Pro

ornith-1.5-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Excellent

Nov 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score
70 vs 86
Hardware Fit
73 vs 92
Quality Score
68 vs 84

Hardware

llama3.1:8b-instru… ornith-1.5-35b-a3b
Machine—GMKtec EVO-X3
CPUC1-ProAMD RYZEN AI MAX+ 395
Cores032
RAM11 GB120 GB
GPUIntegrated / UnknownAMD Radeon(TM) 8060S Graphics
OSunknown unknownMicrosoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modeunknownbalanced

Performance

llama3.1:8b-instru… ornith-1.5-35b-a3b
Tokens/sec6.557.4
First chunk950 ms20 ms
TTFT950 ms367 ms
Load time11.5 s51.1 s
Memory usage4.4 GB66.6 GB
Memory %38%56%

HW Fit Score Breakdown

llama3.1:8b-instruct-q4…

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

ornith-1.5-35b-a3b

Speed
50/50
TTFT
20/20
Memory
22/30

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

ornith-1.5-35b-a3b

Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong 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