Back to leaderboard

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Good

Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor

laguna-xs-2.1

OLLAMA GGUF
Excellent

Aug 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score
78 vs 84
Hardware Fit
86 vs 100
Quality Score
74 vs 77

Hardware

qwen3:8b laguna-xs-2.1
Machine—AZW GTR Pro
CPUAMD Ryzen 9 3900X 12-Core ProcessorAMD RYZEN AI MAX+ 395
Cores2432
RAM64 GB125 GB
GPUNVIDIA GeForce RTX 4060 TiRadeon 8060S
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power

Performance

qwen3:8b laguna-xs-2.1
Tokens/sec48.565.9
First chunk202 ms281 ms
TTFT4.3 s281 ms
Load time4.2 s9.9 s
Memory usage5.5 GB30.1 GB
Memory %9%24%

HW Fit Score Breakdown

qwen3:8b

Speed
50/50
TTFT
6/20
Memory
30/30

laguna-xs-2.1

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

Quality

qwen3:8b

Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

laguna-xs-2.1

Reasoning
8/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
11/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3:8b details | View laguna-xs-2.1 details

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