EAGLE Qwen 2.5 3B Instruct is Rwkv's language model. An EAGLE speculative decoding draft model for Qwen 2.5 3B instruct, accelerating inference through efficient next-token prediction.
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 Qwen 2.5 3B Instruct, ranked by cheapest on-demand price. The model needs about 7 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 | |
|---|---|---|---|---|---|---|
| Standard_NV4as_v4 |  Azure | AMD Radeon Instinct MI25 | 16 GB | $0.233/hr | westus2 | |
| g4ad.xlarge |  AWS | Radeon Pro V520 | 8 GB | $0.379/hr | us-east-1 | |
| g5g.xlarge | AWS | T4g | 16 GB | $0.420/hr | us-east-1 | |
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Qwen Audio 3 Flash Realtime | — | — | $0.413 | $4.13 | Available |
| Qwen Audio 3 Plus Realtime | — | — | $0.688 | $5.50 | Available |
| Qwen Audio 3 Plus TTS | — | — | — | — | Available |
| EAGLE Qwen 2.5 3B Instruct | — | — | — | — | Current |
| Qwen3.7 Plus | 1.0M | $0.320 | $1.28 | Available | |
| Qwen3.7 Max | 1.0M | $1.25 | $3.75 | Available | |
| Qwen3.6 Max Preview | 262K | $1.04 | $6.24 | Available | |
| Qwen3.6 27B | 262K | $0.150 | $0.500 | Available | |
| Qwen3.6 35B A3B | 262K | $0.140 | $0.450 | Available | |
| Qwen3.6 Plus | 1.0M | $0.325 | $1.95 | Available | |
| Qwen3 Max Thinking | 262K | $0.780 | $3.90 | Available |