Back to leaderboard

llama4:scout

OLLAMA GGUF

llama4 · 108.6B · Q4_K_M

Excellent

Oct 3, 2026 · Cortex-X925

laguna-xs-2.1

OLLAMA GGUF
Excellent

Aug 1, 2026 · AMD RYZEN AI MAX+ 395

Global Score
81 vs 84
Hardware Fit
64 vs 100
Quality Score
88 vs 77

Hardware

llama4:scout laguna-xs-2.1
MachineNVIDIA NVIDIA_DGX_SparkAZW GTR Pro
CPUCortex-X925AMD RYZEN AI MAX+ 395
Cores2032
RAM122 GB125 GB
GPUDevice 2e12Radeon 8060S
OSUbuntu 24.04.5 LTSUbuntu 24.04.4 LTS
Archarm64x64
Power Modeperformancelow-power

Performance

llama4:scout laguna-xs-2.1
Tokens/sec19.665.9
First chunk677 ms281 ms
TTFT677 ms281 ms
Load time13.1 s9.9 s
Memory usage63.4 GB30.1 GB
Memory %52%24%

HW Fit Score Breakdown

llama4:scout

Speed
20/50
TTFT
20/20
Memory
24/30

laguna-xs-2.1

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

Quality

llama4:scout

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
13/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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 llama4:scout 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