LFM3-1.7B
Catalog live- Params
- 1.7B
- Min VRAM
- ~4 GB or CPU
- Min RAM
- 8 GB
- Backend
- Ollama
- Fits
- CPU / 4–7 GB GPU
Models
Models on the network
The catalog is small on purpose. One model is registered and supported today; four Qwen3 models are planned. Availability depends on whether a worker is online, not on this page alone.
Access is invite-only for both API calls and contributor invites.
Catalog status
- Catalog live
Registered and supported by the current worker build. It does not guarantee a worker is online.
- In qualification
Under evaluation and not callable. No model is in qualification today.
- Planned
A reviewed target for a later worker build. No download and no API access yet.
Live now
The live catalog
Catalog live means the model is registered and supported. The serving chip reads the public status endpoint every 30 seconds while this tab is visible.
Serving status is unavailable when the public status endpoint cannot be reached. In that case, this page does not guess.
Planned
Planned models
These are reviewed targets for later worker builds. They are not callable and cannot be downloaded today.
Qwen3-8B
Planned- Params
- 8B
- Min VRAM
- 8 GB
- Min RAM
- 16 GB
- Backend
- Ollama
- Fits
- Standard GPU
Qwen3-14B
Planned- Params
- 14B
- Min VRAM
- 12 GB
- Min RAM
- 24 GB
- Backend
- Ollama
- Fits
- Large GPU
Qwen3-30B-A3B
Planned- Params
- 30B-A3B
- Min VRAM
- 20 GB
- Min RAM
- 32 GB
- Backend
- Ollama
- Fits
- XL GPU
Qwen3-32B
Planned- Params
- 32B
- Min VRAM
- 24 GB
- Min RAM
- 32 GB
- Backend
- Ollama
- Fits
- XL+ GPU
Specs
Compare the catalog
Minimum specs are per worker, not per request. A larger card is not a promise of a larger network.
| Model | Params | Min VRAM | Min RAM | Backend | Status | Tier fit |
|---|---|---|---|---|---|---|
| LFM3 1.7B | 1.7B | ~4 GB or CPU | 8 GB | Ollama | Catalog live | CPU / 4–7 GB GPU |
| Qwen3 8B | 8B | 8 GB | 16 GB | Ollama | Planned | Standard GPU |
| Qwen3 14B | 14B | 12 GB | 24 GB | Ollama | Planned | Large GPU |
| Qwen3 30B-A3B | 30B-A3B | 20 GB | 32 GB | Ollama | Planned | XL GPU |
| Qwen3 32B | 32B | 24 GB | 32 GB | Ollama | Planned | XL+ GPU |
LFM3 1.7B
Catalog live- Params
- 1.7B
- Min VRAM
- ~4 GB or CPU
- Min RAM
- 8 GB
- Backend
- Ollama
- Tier fit
- CPU / 4–7 GB GPU
Qwen3 8B
Planned- Params
- 8B
- Min VRAM
- 8 GB
- Min RAM
- 16 GB
- Backend
- Ollama
- Tier fit
- Standard GPU
Qwen3 14B
Planned- Params
- 14B
- Min VRAM
- 12 GB
- Min RAM
- 24 GB
- Backend
- Ollama
- Tier fit
- Large GPU
Qwen3 30B-A3B
Planned- Params
- 30B-A3B
- Min VRAM
- 20 GB
- Min RAM
- 32 GB
- Backend
- Ollama
- Tier fit
- XL GPU
Qwen3 32B
Planned- Params
- 32B
- Min VRAM
- 24 GB
- Min RAM
- 32 GB
- Backend
- Ollama
- Tier fit
- XL+ GPU
Specs are estimates from 4-bit footprints plus ~15% headroom. The signed manifest is authoritative. Minimum specs are per worker, not per request.
Hardware fit
Not sure what your PC can host?
The local check estimates a tier from your hardware. Nothing is uploaded until you ask for an invite.