nemotron-3-super:latest
OLLAMA GGUFnemotron_h_moe · 123.6B · Q4_K_M
Oct 3, 2026 · Cortex-X925
codestral:22b
OLLAMA GGUFllama · 22.2B · Q4_0
Jun 26, 2026 · Cortex-X925
Global Score
74 vs 67
Hardware Fit
50 vs 67
Quality Score
84 vs 67
Hardware
nemotron-3-super:l… codestral:22b
MachineNVIDIA NVIDIA_DGX_SparkNVIDIA NVIDIA_DGX_Spark
CPUCortex-X925Cortex-X925
Cores2020
RAM122 GB122 GB
GPUDevice 2e12Device 2e12
OSUbuntu 24.04.5 LTSUbuntu 24.04.4 LTS
Archarm64arm64
Power Modeperformanceperformance
Performance
nemotron-3-super:l… codestral:22b
Tokens/sec21.817.2
First chunk420 ms129 ms
TTFT2.2 s129 ms
Load time12.4 s11.6 s
Memory usage79.5 GB18.9 GB
Memory %65%16%
HW Fit Score Breakdown
nemotron-3-super:latest
Speed
23/50
TTFT
10/20
Memory
17/30
codestral:22b
Speed
17/50
TTFT
20/20
Memory
30/30
Quality
nemotron-3-super:latest
Reasoning
17/20
Coding
18/20
Instruction
11/20
Structured
14/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
codestral:22b
Reasoning
11/20
Coding
17/20
Instruction
9/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Strong Math: Weak Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest