Back to leaderboard

qwen3.8:27b

OLLAMA GGUF

qwen35 · 27.3B · Q4_K_M

Excellent

Aug 15, 2026 · Cortex-X925

laguna-xs-2.1

OLLAMA GGUF
Excellent

Aug 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score
85 vs 84
Hardware Fit
79 vs 100
Quality Score
87 vs 77

Hardware

qwen3.8:27b laguna-xs-2.1
MachineASUSTeK COMPUTER INC. GX10AZW GTR Pro
CPUCortex-X925AMD RYZEN AI MAX+ 395
Cores2032
RAM122 GB125 GB
GPUDevice 2e12Radeon 8060S
OSUbuntu 24.04.4 LTSUbuntu 24.04.4 LTS
Archarm64x64
Power Modeperformancelow-power

Performance

qwen3.8:27b laguna-xs-2.1
Tokens/sec27.465.9
First chunk593 ms281 ms
TTFT593 ms281 ms
Load time0.3 s9.9 s
Memory usage18.2 GB30.1 GB
Memory %15%24%

HW Fit Score Breakdown

qwen3.8:27b

Speed
29/50
TTFT
20/20
Memory
30/30

laguna-xs-2.1

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

Quality

qwen3.8:27b

Reasoning
18/20
Coding
17/20
Instruction
16/20
Structured
15/15
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