Gemma 3 4B It GGUF

Gemma 3 4B It GGUF is a text model from Lemonade (AMD) with a context window of 128K tokens and max output of 8K tokens.

Capabilities

Vision Function Calling Reasoning JSON Schema System Messages Web Search Prompt Caching Audio Input Audio Output

Specifications

Model Keylemonade/Gemma-3-4b-it-GGUF
ProviderLemonade (AMD)
Provider IDlemonade
ModeText
Canonical Namegemma-3-4b
Context Window128K tokens
Max Output8K tokens

Pricing

TypePer 1K TokensPer 1M Tokens
Input TokensN/AN/A
Output TokensN/AN/A

Benchmarks

Intelligence Index6.3#233
Coding Index2.9#167
Math Index12.7#116
MMLU-Pro0.4#178
GPQA0.3#208
HLE0.1#93
LiveCodeBench0.1#174
AIME0.1#98
IFBench0.3#148
Time to First Token1.12s#184
SciCode0.1#204
MATH-5000.8#78
AIME 20250.1#116
LCR0.1#141
TerminalBench Hard0.0#138
TAU20.1#153

Price Comparison by Provider

Compare prices for Gemma 3 4B It GGUF across different providers. The same model may be available through multiple providers at different price points.

Provider
Model Key
Input Price, $
Output Price, $
LlamaGatellamagate/gemma3-4b0.0300.080
Lemonade (AMD)lemonade/Gemma-3-4b-it-GGUFN/AN/A
AWS Bedrockgoogle.gemma-3-4b-it0.0400.080
DeepInfradeepinfra/google/gemma-3-4b-it0.0400.080

All Variants

All available versions, regions, and API endpoints for Gemma 3 4B It GGUF.

Model Key
Provider
Mode
Input Price, $
Output Price, $
Context
Max Output
Vision
Functions
google.gemma-3-4b-itAWS BedrockText0.0400.080128K8Kyesno
deepinfra/google/gemma-3-4b-itDeepInfraText0.0400.080131K131Knoyes
lemonade/Gemma-3-4b-it-GGUFLemonade (AMD)TextN/AN/A128K8Knoyes
llamagate/gemma3-4bLlamaGateText0.0300.080128K8Kyesyes