Back to leaderboard

qwen3.8:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Aug 15, 2026 · AMD RYZEN AI MAX+ 395

laguna-xs-2.1

OLLAMA GGUF
Excellent

Aug 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score
80 vs 84
Hardware Fit
66 vs 100
Quality Score
86 vs 77

Hardware

qwen3.8:27b laguna-xs-2.1
MachineAZW GTR ProAZW GTR Pro
CPUAMD RYZEN AI MAX+ 395AMD RYZEN AI MAX+ 395
Cores3232
RAM125 GB125 GB
GPURadeon 8060SRadeon 8060S
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archx64x64
Power Modelow-powerlow-power

Performance

qwen3.8:27b laguna-xs-2.1
Tokens/sec18.465.9
First chunk587 ms281 ms
TTFT587 ms281 ms
Load time7.4 s9.9 s
Memory usage17.4 GB30.1 GB
Memory %14%24%

HW Fit Score Breakdown

qwen3.8:27b

Speed
17/50
TTFT
19/20
Memory
30/30

laguna-xs-2.1

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

Quality

qwen3.8:27b

Reasoning
17/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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 qwen3.8:27b 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