Back to leaderboard

nemotron3:33b

OLLAMA GGUF

nemotron_h_omni · 33.0B · Q4_K_M

Excellent

Jun 28, 2026 · AMD RYZEN AI MAX+ 395

llama4:scout

OLLAMA GGUF

llama4 · 108.6B · Q4_K_M

Excellent

Oct 3, 2026 · Cortex-X925

Global Score
96 vs 81
Hardware Fit
95 vs 64
Quality Score
97 vs 88

Hardware

nemotron3:33b llama4:scout
MachineAZW GTR ProNVIDIA NVIDIA_DGX_Spark
CPUAMD RYZEN AI MAX+ 395Cortex-X925
Cores3220
RAM125 GB122 GB
GPURadeon 8060SDevice 2e12
OSUbuntu 24.04.4 LTSUbuntu 24.04.5 LTS
Archx64arm64
Power Modelow-powerperformance

Performance

nemotron3:33b llama4:scout
Tokens/sec62.719.6
First chunk372 ms677 ms
TTFT1.0 s677 ms
Load time13.1 s13.1 s
Memory usage24.4 GB63.4 GB
Memory %20%52%

HW Fit Score Breakdown

nemotron3:33b

Speed
50/50
TTFT
15/20
Memory
30/30

llama4:scout

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

Quality

nemotron3:33b

Reasoning
19/20
Coding
18/20
Instruction
20/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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
View nemotron3:33b details | View llama4:scout 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