Google · TimesFM
TimesFM 3.0
Verified by Badgr · RunTimesFM 3.0 is a 0.33B time-series-forecasting model available through supported Badgr execution routes.
Last validated or meaningfully updated: 2026-10-10
✓ Verified by Badgr · PyTorch · Run
Last verified 2026-10-10
badgr run --image vllm/vllm-openai:v0.30.0 --gpu RTX_4090 --funding paid --max-cost 1.5 --max-runtime 30 --cmd 'pip install timesfm[torch] ... timesfm.TimesFM3Forecaster.from_pretrained("google/timesfm-3.0-pytorch").predict(series, horizon=48)'- GPU
- NVIDIA RTX A5000Reported by the provider, not confirmed inside the container
- Command runtime
- 150s
- Deployment
- dep-e2c5ab0dd0
- ✓ Workload container started
- ✓ Command exited with code 0
- ✓ A 48-step forecast was produced from a 400-point series
- ✓ Forecast error against the true continuation: 0.002 (repeat-last-value baseline: 0.806)
- ✓ Teardown completed
A synthetic daily-seasonal series with a small trend, not real data. The request asked for an RTX 4090 and the job reported an RTX A5000. The model card has no usage instructions; the timesfm package's TimesFM3Forecaster class was used. The command is abridged and the elapsed time is estimated.
Raw evidence
deployment=dep-e2c5ab0dd0 status=succeeded user_command_exit=0 gpu NVIDIA RTX A5000 | forecast len 48 | MAE vs true continuation 0.002 | baseline MAE (repeat last value) 0.806 | 7.4s
Run from Badgr's local development environment. Documents that this job works end-to-end for this model.
Availability
Not yet Badgr AI API
Not currently validated
✓ Dedicated endpoint
Available through Badgr
✓ Custom GPU deployment
Available through Badgr
Deployment profile
- Architecture
- TimesFM3Torch
- Licence
- TimesFM Non-Commercial
- Minimum VRAM
- ~5GB
- Context
- Task dependent
Recommended: RTX 4090 24GB. VRAM is an estimate and increases with context, cache, concurrency, and runtime overhead.
Model identity
- Updated
- 1 months ago
- HuggingFace revision
- 43046b85ec
Popularity and trust
Downloads (last month)
1.0M
Likes
938
Spaces using this model
19
Files and formats
Weight formats
Safetensors
Repository files
5
Chat template
Not detected
GPU deployment scenarios
Estimated from parameter count and quantisation. Will switch to “Verified by Badgr” once a real run backs a tier.
Testing
RTX 4090 24GB
Short context, low concurrency
Small production
L40S 48GB
8K context, 1-4 concurrent requests
Higher throughput
A100 80GB
32K context, continuous batching
Large production
RTX 4090 24GB
Higher concurrency
Estimated — multimodal inputs, long context, and concurrency all increase real VRAM use beyond this estimate.
Also runs well on L40S 48GB, A100 40GB. Available in United States, Europe.
Serving compatibility
| Runtime | Status | Notes |
|---|---|---|
| vLLM | Estimated | Used for Badgr dedicated endpoints |
| Transformers | Unknown | Basic fallback |
| llama.cpp | Requires GGUF conversion | No GGUF weights found in repo |
| SGLang | Unknown | Not evaluated |
| Ollama | Unknown | Not evaluated |
| Diffusers | Unknown | Not evaluated |
| PyTorch | Verified for Run | Confirmed by a real badgr run job (deployment dep-e2c5ab0dd0); serving is not verified |
| TensorRT-LLM | Unknown | Conversion may be required |
| TGI | Unknown | Not evaluated |
Ready-to-run Badgr configurations
Quick test
badgr serve google/timesfm-3.0-pytorch --max-cost 2Validated dedicated endpoint command
badgr serve google/timesfm-3.0-pytorch --gpu RTX 4090 --max-cost 10Advanced configuration (defaults to automatic)
- Runtime
- Quantisation
- GPU and GPU count
- Context length
- Maximum concurrency
- Region
- Maximum hourly spend
- Persistent or capped runtime
Estimated pricing
Provider estimate: cold start
2–5 min
Provider estimate: endpoint cost
$0.20 – $0.45/hr
Idle cost
$0 when stopped
Per-token throughput cost is not shown here: Badgr has not benchmarked this model yet, and this page does not display figures it cannot back with real data.
Recommended Badgr routes
RTX 4090 24GB · United States
Availablefrom $0.20/hr
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: just now
RTX 4090 24GB · United States
Availablefrom $0.39/hr
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: just now
RTX 4090 24GB · United States
Availablefrom $0.43/hr
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: just now
RTX 4090 24GB · United States
Availablefrom $0.44/hr
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: just now
RTX 4090 24GB · Europe
Estimatedstarting from $0.45/hr
Badgr estimated starting price
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: Live marketplace price not available yet
RTX 4090 24GB · Europe
Estimatedstarting from $0.45/hr
Badgr estimated starting price
Best for
ComfyUI, Batch Inference, Qwen 2.5 7B Instruct
Startup: 2–5 min
Reliability: Standard
Last checked: Live marketplace price not available yet
Known limitations
- Memory use increases with context length and concurrency.