Run Llama 3.3 70B Speculative Decoding on your data

Llama 3.3 70B Speculative Decoding is an LLM that excels in fast inference and high-performance language processing tasks. It leverages speculative decoding to achieve significantly improved output speeds, making it particularly suitable for real-time AI applications and tasks requiring rapid response times.

Some other noteworthy features of Llama 3.3 70B Speculative Decoding include enhanced performance in coding, reasoning, math, general knowledge tasks, instruction following, and tool use.

Metric	Value
Parameter Count	70 billion
Mixture of Experts	No
Context Length	8,192 tokens
Multilingual	Yes
Quantized*	Unknown

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.

	Modality	Price (1M tokens)
Llama 3.1 405B Instruct	Fireworks AI	text	text	$3.00	$3.00
Llama 3.1 405B Instruct Turbo	Together.ai	text	text	$3.50	$3.50
Llama 3.1 70B Instruct	Fireworks AI	text	text	$0.90	$0.90
Llama 3.1 70B Instruct Turbo	Together.ai	text	text	$0.88	$0.88
Llama 3.1 8B	Groq	text	text	$0.05	$0.08
Llama 3.1 8B Instruct	Fireworks AI	text	text	$0.20	$0.20
Llama 3.1 8B Instruct Turbo	Together.ai	text	text	$0.18	$0.18
Llama 3.1 Nemotron 70B Instruct	Together.ai	text	text	$0.90	$0.90
Llama 3.2 11B Vision	Groq	image	text	$0.18	$0.18
Llama 3.2 1B	Groq	text	text	$0.04	$0.04
Llama 3.2 3B	Groq	text	text	$0.06	$0.06
Llama 3.2 3B Instruct Turbo	Together.ai	text	text	$0.06	$0.06
Llama 3.2 90B Vision (Preview)	Groq	image	text	$0.90	$0.90
Llama 3.3 70B Instruct	Fireworks AI	text	text	$0.90	$0.90
Llama 3.3 70B Instruct Turbo	Together.ai	text	text	$0.88	$0.88
Llama 3.3 70B Speculative Decoding	Groq	text	text	$0.59	$0.59
Llama 3.3 70B Versatile 128k	Groq	text	text	$0.59	$0.79

Modality

Price (1M tokens)

Model

Inference provider

Input

Output

Input

Output

Llama 3.1 405B Instruct

Fireworks AI