GPT-OSS 20B (GGUF, Q4_K_M)
Production-ready GGUF quantization of ggml-org/gpt-oss-20b for distributed text generation and conversation — powered by the Aether edge inference runtime.
Highlights
- 20B parameters — Open-source GPT 20B model. Large-scale text generation for distributed inference.
- ~20 GB Q4_K_M quantized — optimized for distributed edge inference
- GPT-OSS architecture — proven, stable, well-tested
- Aether runtime compatible — layer-sharded across distributed nodes via Edgework.ai
Model Details
| Property | Value |
|---|---|
| Base model | ggml-org/gpt-oss-20b |
| Parameters | 20B |
| Architecture | GPT-OSS |
| Quantization | Q4_K_M |
| Format | GGUF |
| Size | ~20 GB |
| License | apache-2.0 |
Usage
With llama.cpp
./llama-cli -m gpt-oss-20b-q4_k_m.gguf -p "Your prompt here" -n 256
With Aether (Distributed Inference)
This model is deployed across the Aether distributed inference network. Weights are layer-sharded and distributed across multiple edge nodes for parallel inference.
Deployment Architecture
This model runs on the Aether distributed inference runtime — our custom engine that shards model layers across multiple nodes for parallel execution:
- Coordinator receives requests and manages token generation
- Layer nodes each hold a subset of model layers
- Hidden states flow between nodes via gRPC
- Zero cold start via warm pool scheduling
Deployed via Edgework.ai — bringing fast, cheap, and private inference as close to the user as possible.
About
Published by AFFECTIVELY · Managed by @buley
We quantize and publish production-ready models for distributed edge inference via the Aether runtime. Every release is tested for correctness and stability before publication.