Instructions to use mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1

SGLang

How to use mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1 with Docker Model Runner:
```
docker model run hf.co/mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1
```

vLLM support is...

by mrs83 - opened 8 days ago

Discussion

mrs83

Owner 8 days ago

...work in progress!

mrs83

Owner 8 days ago

•

edited 8 days ago

Inference Benchmark — `echo-hybrid`

Inference benchmark on single AMD Radeon AI Pro R9700

Endpoint: http://localhost:8001/v1
Prompt: Explain the concept of recursion briefly.
Max tokens: 64 · Warmup: 2 req · Date: 2026-05-16 13:15 UTC

Concurrency	Throughput (req/s)	TTFT p50	TTFT p95	Latency p50	Latency p95
1	0.88	48 ms	57 ms	1137 ms	1152 ms
2	1.69	58 ms	83 ms	1187 ms	1199 ms
4	3.35	74 ms	86 ms	1193 ms	1203 ms
8	5.19	82 ms	91 ms	1540 ms	1548 ms
16	10.21	74 ms	97 ms	1565 ms	1584 ms
32	20.34	94 ms	109 ms	1570 ms	1584 ms

mrs83

Owner 7 days ago

Inference benchmark on single AMD Instinct MI300X VF - vLLM on ROCm 7.2.0

Inference Benchmark — `echo-hybrid`

Endpoint: http://127.0.0.1:8001/v1
Prompt: Explain the concept of recursion briefly.
Max tokens: 256 · Warmup: 2 req · Date: 2026-05-16 15:58 UTC

Concurrency	Throughput (req/s)	TTFT p50	TTFT p95	Latency p50	Latency p95
1	0.24	73 ms	83 ms	3826 ms	7277 ms
2	0.45	98 ms	115 ms	3832 ms	7711 ms
4	0.76	101 ms	114 ms	4439 ms	7897 ms
8	1.15	108 ms	124 ms	5527 ms	9148 ms
16	2.10	113 ms	133 ms	6180 ms	9307 ms
32	4.20	113 ms	131 ms	5889 ms	9339 ms
64	7.87	120 ms	140 ms	6598 ms	10047 ms

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

vLLM support is...

Inference Benchmark — echo-hybrid

Inference Benchmark — echo-hybrid

Inference Benchmark — `echo-hybrid`

Inference Benchmark — `echo-hybrid`