Qwen/Qwen2.5-0.5B-Instruct-GGUF
Yes. Umbra lists this public Hugging Face GGUF in its hosted API catalog. When an eligible attested provider is online, call it through the OpenAI- or Anthropic-compatible API using the exact model ID below.
hf-qwen-qwen2.5-0.5b-instruct-gguf-qwen2-5-0-5b-instruct-fp16https://api.tryumbra.dev/v1This catalog entry is missing at least one field needed for an exact artifact claim. Verify the repository, revision, filename, and digest before relying on it.
9217f5db79a29953eb74d5343926648285ec7e678e0ae26000627ed62de0e78e41860af70094558b9d2913385c842a6aa06cf3fcThe API key is the only secret. Never place a real key in a model card, browser page, or repository.
from openai import OpenAI
client = OpenAI(
base_url="https://api.tryumbra.dev/v1",
api_key="umbra-...",
)
response = client.chat.completions.create(
model="hf-qwen-qwen2.5-0.5b-instruct-gguf-qwen2-5-0-5b-instruct-fp16",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.tryumbra.dev/v1",
apiKey: "umbra-...",
});
const response = await client.chat.completions.create({
model: "hf-qwen-qwen2.5-0.5b-instruct-gguf-qwen2-5-0-5b-instruct-fp16",
messages: [{ role: "user", content: "Hello" }],
});
console.log(response.choices[0].message.content);from anthropic import Anthropic
client = Anthropic(
base_url="https://api.tryumbra.dev",
api_key="umbra-...",
default_headers={"anthropic-version": "2023-06-01"},
)
message = client.messages.create(
model="hf-qwen-qwen2.5-0.5b-instruct-gguf-qwen2-5-0-5b-instruct-fp16",
max_tokens=512,
messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)If you maintain the repository, this short block gives users an honest hosted-API link. Keep it only while the catalog page remains accurate.
## Hosted API
This GGUF is available through [Umbra](https://tryumbra.dev/models/hf-qwen-qwen2.5-0.5b-instruct-gguf-qwen2-5-0-5b-instruct-fp16/), an OpenAI- and Anthropic-compatible API for public Hugging Face models served from attested Apple Silicon.
- Model ID: `hf-qwen-qwen2.5-0.5b-instruct-gguf-qwen2-5-0-5b-instruct-fp16`
- API details and live availability: https://tryumbra.dev/models/hf-qwen-qwen2.5-0.5b-instruct-gguf-qwen2-5-0-5b-instruct-fp16/Yes. Umbra lists this public Hugging Face GGUF under the model ID hf-qwen-qwen2.5-0.5b-instruct-gguf-qwen2-5-0-5b-instruct-fp16. Calls are accepted while an eligible attested provider is online.
Yes. Use https://api.tryumbra.dev/v1 as the OpenAI base URL. Umbra also exposes an Anthropic-compatible messages endpoint.
Umbra’s catalog record does not yet publish every field needed to identify one exact artifact: repository, immutable revision, GGUF filename, and SHA-256 digest. Review the provenance fields below before use.
No. Prompts and outputs are decrypted in process, held in memory for the request, and never logged or persisted.
The current catalog memory floor is 8 GB of unified memory.