EAGLE Llama 3 8B Instruct is Rwkv's language model. An EAGLE speculative decoding draft model for Llama 3.x 8B instruct, enabling faster inference through efficient token prediction.
Specifications
Canonical IDrwkv-eagle-llama-3-8b-instruct
TypeLanguage
StatusActive
CreatorRwkv
Input ModalitiesText
Output ModalitiesText
Parameters8B

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Cheapest Instances to Run It

Cloud GPU instances that can host EAGLE Llama 3 8B Instruct, ranked by cheapest on-demand price. The model needs about 19 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
g2-standard-4GCPnvidia-l424 GB$0.705/hr
g6.xlargeAWSL422 GB$0.805/hr
g2-standard-8GCPnvidia-l424 GB$0.851/hr
7 more instances can run EAGLE Llama 3 8B Instruct
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Llama 3.2 11B128K$0.160$0.160Available
Llama 3.2 11B Instruct128K$0.160$0.160Deprecated
Llama 3.1 405B Instruct131K$0.120$0.300Deprecated
Llama 3.1 70B128K$0.360$0.360Deprecated
Llama 3.1 70B Instruct131K$0.100$0.100Deprecated
Llama 3.1 8B131K$0.030$0.050Deprecated
Llama 3.1 8B Instruct200K$0.020$0.030Deprecated
Llama 3 70B Instruct131K$0.120$0.300Deprecated
Llama 3 8B Instruct32K$0.030$0.040Deprecated
EAGLE Llama 3 8B Instruct————Current
Dolphin 3 8B—128K$0.080$0.150Available

Model IDs

accounts/fireworks/models/eagle-llama-v3-8b-instruct-v1
accounts/fireworks/models/eagle-llama-v3-8b-instruct-v2
rwkv-eagle-llama-3-8b-instruct