LLM Comparison

Maple-Preview vs Nemotron 3 Nano 30B A3B

Side-by-side specs, pricing & capabilities · Updated October 2026

Add to comparison

2/6 models
Same tier:
 DeepGroveMaple-PreviewNVIDIANemotron 3 Nano 30B A3B
OrganizationDeepGroveDeepGroveNVIDIANVIDIA
OpenTools Score
45
FamilyMapleNemotron
StatusCurrentCurrent
Release DateAug 2026Dec 2025
Context Window131K tokens256K tokens
Input Price——
Output Price——
Pricing NotesOpen-source model card; no hosted API pricing found in the official source. Local inference costs depend on user hardware and runtime.Free tier available on OpenRouter with rate limits
Capabilities
textreasoningcodeon-device-inference
textcode
API Identifierdeepgrove/maple-previewnvidia/nemotron-3-nano-30b-a3b:free
Benchmarks
LiveCodeBench v6
75.1DeepGrove model card
—
AIME 2026
87.5DeepGrove model card
—
HMMT 2026
78.8DeepGrove model card
—
GPQA Diamond
73.5DeepGrove model card
—
 View Maple-PreviewView Nemotron 3 Nano 30B A3B

DeepGrove

Maple-Preview

Maple-Preview is DeepGrove’s open-source 20B-A1B ternary-weight reasoning LLM for efficient on-device inference. The model card reports 20.2B total parameters, 1.49B active parameters, a 131,072-token context window, and 5.31 GB checkpoint size. The model card specifies 131,072 tokens of context but does not establish a separate maximum output-token limit.

NVIDIA

Nemotron 3 Nano 30B A3B

Nemotron 3 Nano 30B A3B is a large language model from NVIDIA. Supports up to 256,000 token context window. Available free with rate limits on OpenRouter.

More Comparisons

Flagship

GPT-6.1 Sol vs Claude Sonnet 5.5

Flagship

GPT-6.1 Sol vs Grok 4.7

Flagship

GPT-6.1 Sol vs Gemini 3.6 Flash

Flagship

GPT-6.1 Sol vs Palmyra X5

Flagship

GPT-6.1 Sol vs Jamba Large 1.7

Flagship

GPT-6.1 Sol vs Command A

Looking for more AI models?

Browse All LLMs