Instructions to use IFM/K2-Horizon-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IFM/K2-Horizon-32B with Transformers:

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

pipe = pipeline("text-generation", model="IFM/K2-Horizon-32B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("IFM/K2-Horizon-32B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IFM/K2-Horizon-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IFM/K2-Horizon-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IFM/K2-Horizon-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IFM/K2-Horizon-32B

SGLang

How to use IFM/K2-Horizon-32B 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 "IFM/K2-Horizon-32B" \
    --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": "IFM/K2-Horizon-32B",
		"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 "IFM/K2-Horizon-32B" \
        --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": "IFM/K2-Horizon-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IFM/K2-Horizon-32B with Docker Model Runner:
```
docker model run hf.co/IFM/K2-Horizon-32B
```

aaryamonvikram commited on 12 days ago

Commit

a3c84c2

verified ·

1 Parent(s): abac703

Updated K2-Horizon-MoVA-36B-A4B

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -39,7 +39,7 @@ K2-Horizon is released as a family of checkpoints that share the same post-train
 | K2-Horizon-3.7B | XllmForCausalLM; dense decoder-only | 5.06B | 5.06B | 524,288 | 250,624 | Efficient research, evaluation, and single-node serving |
 | K2-Horizon-7B | XllmForCausalLM; dense decoder-only | 9.00B | 9.00B | 524,288 | 250,624 | General research, fine-tuning, and cost-conscious deployment |
 | K2-Horizon-32B | K2HorizonForCausalLM; dense decoder-only | 34.78B | 34.78B | 524,288 | 250,624 | Stronger long-context and reasoning experiments |
-| K2-Horizon-36B | K2HorizonForCausalLM; MoVA + MoE | 37.44B | 5.95B | 524,288 | 250,624 | Multistage research and production-style serving experiments |
 | K2-Horizon-375B | XllmForCausalLM; sparse MoE | 379.17B | 26.67B | 524,288 | 250,624 | Frontier-scale open research, long-context evaluation, and high-capacity serving |
 Tokenizer files are distributed with each model repository. The compact K2-Horizon-0.9B model comes from the IFM Mobile line and uses a 64,256-token vocabulary. The 3.7B, 7B, 32B, 36B, and 375B models use a 250,624-token vocabulary.
@@ -404,7 +404,7 @@ The table below gives capacity-planning starting points for self-hosted inferenc
 | K2-Horizon-3.7B | 5.06B | 5.06B | 9.4 GiB | 18.8 GiB | 18.0 GiB @ 128K tokens | 1 | 1 GPU with 24 GiB can serve short contexts in BF16; use 48-80 GiB for larger KV caches and 128K-class requests. |
 | K2-Horizon-7B | 9.00B | 9.00B | 16.8 GiB | 33.5 GiB | 18.0 GiB @ 128K tokens | 1 | 1 GPU with 40-48 GiB is suitable for short-context BF16 serving; 80 GiB is the practical starting point for 128K-class requests. |
 | K2-Horizon-32B | 34.78B | 34.78B | 64.8 GiB | 129.6 GiB | 32.0 GiB @ 128K tokens | 2-4 | 1x 80 GiB fits BF16 weights only at short context; start with 2x 80 GiB for 128K requests and 4x 80 GiB for larger context or throughput. |
-| K2-Horizon-36B | 37.44B | 5.95B | 69.7 GiB | 139.5 GiB | 24.0 GiB @ 128K tokens | 2-4 | Use at least 256 GiB of host RAM to load the current 139.5 GiB FP32 shard set. Start with 2x 80 GiB GPUs for BF16 weight sharding, or 1x H200 141 GiB for short single-request validation; use 4x 80 GiB for 128K-class requests. |
 | K2-Horizon-375B | 379.17B | 26.67B | 706.3 GiB | 1.38 TiB | 30.5 GiB @ 128K tokens | 8 H200 or 16x 80 GiB | The full 512K profile is validated on 8x H200 141 GiB GPUs at TP=8 and 0.92 memory utilization; use at least 16x 80 GiB GPUs on lower-memory hardware. |
 ## Evaluation
@@ -419,7 +419,7 @@ Benchmark values are reported as percentages unless otherwise noted. A dash mean
 | K2-Horizon-3.7B | `mid_4_final` | 85.7 | 73.0 | 80.7 | 84.4 |
 | K2-Horizon-7B | `mid_4_final` | 89.9 | 75.7 | 83.3 | 87.8 |
 | K2-Horizon-32B | `mid_4_final` | 88.0 | 79.5 | 87.5 | 89.1 |
-| K2-Horizon-36B | `mid_4_final` | 89.6 | 79.2 | 87.3 | 88.6 |
 | K2-Horizon-375B | `mid_4_final` | 92.1 | 82.6 | 89.5 | 87.5 |
 ### Family Evaluation: STEM, Reasoning, and Coding
@@ -430,7 +430,7 @@ Benchmark values are reported as percentages unless otherwise noted. A dash mean
 | K2-Horizon-3.7B | `mid_4_final` | 88.2 | 73.3 | 92.3 | 86.4 |
 | K2-Horizon-7B | `mid_4_final` | 87.6 | 73.9 | 95.1 | 91.0 |
 | K2-Horizon-32B | `mid_4_final` | 91.7 | 75.4 | 95.5 | 87.8 |
-| K2-Horizon-36B | `mid_4_final` | 92.7 | 75.4 | 95.2 | 87.2 |
 | K2-Horizon-375B | `mid_4_final` | 92.5 | 84.9 | 95.1 | 93.8 |
 ### Family Evaluation: Agentic and Long-Context Tasks

 | K2-Horizon-3.7B | XllmForCausalLM; dense decoder-only | 5.06B | 5.06B | 524,288 | 250,624 | Efficient research, evaluation, and single-node serving |
 | K2-Horizon-7B | XllmForCausalLM; dense decoder-only | 9.00B | 9.00B | 524,288 | 250,624 | General research, fine-tuning, and cost-conscious deployment |
 | K2-Horizon-32B | K2HorizonForCausalLM; dense decoder-only | 34.78B | 34.78B | 524,288 | 250,624 | Stronger long-context and reasoning experiments |
+| K2-Horizon-MoVA-36B-A4B | K2HorizonForCausalLM; MoVA + MoE | 37.44B | 5.95B | 524,288 | 250,624 | Multistage research and production-style serving experiments |
 | K2-Horizon-375B | XllmForCausalLM; sparse MoE | 379.17B | 26.67B | 524,288 | 250,624 | Frontier-scale open research, long-context evaluation, and high-capacity serving |
 Tokenizer files are distributed with each model repository. The compact K2-Horizon-0.9B model comes from the IFM Mobile line and uses a 64,256-token vocabulary. The 3.7B, 7B, 32B, 36B, and 375B models use a 250,624-token vocabulary.
 | K2-Horizon-3.7B | 5.06B | 5.06B | 9.4 GiB | 18.8 GiB | 18.0 GiB @ 128K tokens | 1 | 1 GPU with 24 GiB can serve short contexts in BF16; use 48-80 GiB for larger KV caches and 128K-class requests. |
 | K2-Horizon-7B | 9.00B | 9.00B | 16.8 GiB | 33.5 GiB | 18.0 GiB @ 128K tokens | 1 | 1 GPU with 40-48 GiB is suitable for short-context BF16 serving; 80 GiB is the practical starting point for 128K-class requests. |
 | K2-Horizon-32B | 34.78B | 34.78B | 64.8 GiB | 129.6 GiB | 32.0 GiB @ 128K tokens | 2-4 | 1x 80 GiB fits BF16 weights only at short context; start with 2x 80 GiB for 128K requests and 4x 80 GiB for larger context or throughput. |
+| K2-Horizon-MoVA-36B-A4B | 37.44B | 5.95B | 69.7 GiB | 139.5 GiB | 24.0 GiB @ 128K tokens | 2-4 | Use at least 256 GiB of host RAM to load the current 139.5 GiB FP32 shard set. Start with 2x 80 GiB GPUs for BF16 weight sharding, or 1x H200 141 GiB for short single-request validation; use 4x 80 GiB for 128K-class requests. |
 | K2-Horizon-375B | 379.17B | 26.67B | 706.3 GiB | 1.38 TiB | 30.5 GiB @ 128K tokens | 8 H200 or 16x 80 GiB | The full 512K profile is validated on 8x H200 141 GiB GPUs at TP=8 and 0.92 memory utilization; use at least 16x 80 GiB GPUs on lower-memory hardware. |
 ## Evaluation
 | K2-Horizon-3.7B | `mid_4_final` | 85.7 | 73.0 | 80.7 | 84.4 |
 | K2-Horizon-7B | `mid_4_final` | 89.9 | 75.7 | 83.3 | 87.8 |
 | K2-Horizon-32B | `mid_4_final` | 88.0 | 79.5 | 87.5 | 89.1 |
+| K2-Horizon-MoVA-36B-A4B | `mid_4_final` | 89.6 | 79.2 | 87.3 | 88.6 |
 | K2-Horizon-375B | `mid_4_final` | 92.1 | 82.6 | 89.5 | 87.5 |
 ### Family Evaluation: STEM, Reasoning, and Coding
 | K2-Horizon-3.7B | `mid_4_final` | 88.2 | 73.3 | 92.3 | 86.4 |
 | K2-Horizon-7B | `mid_4_final` | 87.6 | 73.9 | 95.1 | 91.0 |
 | K2-Horizon-32B | `mid_4_final` | 91.7 | 75.4 | 95.5 | 87.8 |
+| K2-Horizon-MoVA-36B-A4B | `mid_4_final` | 92.7 | 75.4 | 95.2 | 87.2 |
 | K2-Horizon-375B | `mid_4_final` | 92.5 | 84.9 | 95.1 | 93.8 |
 ### Family Evaluation: Agentic and Long-Context Tasks