Instructions to use MultiverseComputingCAI/Hypernova-60B-2605 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MultiverseComputingCAI/Hypernova-60B-2605 with Transformers:

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

pipe = pipeline("text-generation", model="MultiverseComputingCAI/Hypernova-60B-2605")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MultiverseComputingCAI/Hypernova-60B-2605")
model = AutoModelForCausalLM.from_pretrained("MultiverseComputingCAI/Hypernova-60B-2605")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MultiverseComputingCAI/Hypernova-60B-2605 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MultiverseComputingCAI/Hypernova-60B-2605"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MultiverseComputingCAI/Hypernova-60B-2605",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MultiverseComputingCAI/Hypernova-60B-2605

SGLang

How to use MultiverseComputingCAI/Hypernova-60B-2605 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 "MultiverseComputingCAI/Hypernova-60B-2605" \
    --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": "MultiverseComputingCAI/Hypernova-60B-2605",
		"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 "MultiverseComputingCAI/Hypernova-60B-2605" \
        --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": "MultiverseComputingCAI/Hypernova-60B-2605",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MultiverseComputingCAI/Hypernova-60B-2605 with Docker Model Runner:
```
docker model run hf.co/MultiverseComputingCAI/Hypernova-60B-2605
```

HyperNova 60B 2605

Powered by CompactifAI

Optimized for Efficient Inference · Reduced Memory Footprint · Native Tool Calling Support

Highlights
Model Overview
Key Characteristics
Quick Start
What's New in HyperNova 60B 2605
Tool Calling
Training & Fine-Tuning
Architecture
Evaluation & Benchmarks
Languages
Intended Use
Safety & Limitations
Model Information
Citation

Model Overview

HyperNova 60B 2605, developed by Multiverse Computing, is an open-weight model designed for powerful general reasoning, coding, and versatile developer use.

The model is instruction-tuned and supports native tool calling (function calling with defined schemas, structured outputs, and agent-style workflows). HyperNova 60B 2605 is intended for code generation, RAG, and tool-augmented applications.

Technical Deep Dive

For a detailed explanation of the compression architecture, model compression process, and benchmark results behind Hypernova-60B, read this full technical article by Johanna Angulo, Evaluation Manager at Multiverse Computing.

Key Characteristics

Characteristic	Description
🛠️ Tool calling	Native support; OpenAI-style function / tool calling schemas; suited to coding agents and structured outputs
🧠 Parameters	60B total parameters
📐 Architecture	Decoder-only Transformer
Primary language	English
Other languages	Not formally evaluated

Quick Start

This model can be loaded with the Transformers API. Use trust_remote_code=True (required for the gpt-oss architecture). Recommended approach: AutoModelForCausalLM with apply_chat_template:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "MultiverseComputingCAI/HyperNova-60B-2605"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
    trust_remote_code=True,
)
messages = [{"role": "user", "content": "What is a Hypernova?"}]
inputs = tokenizer.apply_chat_template(
    messages,
    return_tensors="pt",
    add_generation_prompt=True,
)
inputs = inputs.to(model.device)
attention_mask = torch.ones_like(inputs, dtype=torch.long, device=inputs.device)
outputs = model.generate(
    inputs,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    attention_mask=attention_mask,
)
reply = tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True)
print(reply)

Alternatively you can use the pipeline API with trust_remote_code=True; the pipeline returns the full conversation structure, so extract the assistant message from outputs[0]["generated_text"] as needed.

What’s New in HyperNova 60B 2605

HyperNova 60B 2605 is an improved version of HyperNova 60B 2602, with this release focused on coding and general capability backed by higher scores on several benchmarks.

Summary

Improvement focus vs HyperNova 60B 2602: stronger coding (coding-style tasks) and general benchmark performance.
Tool use: Retains native support for function calling, structured outputs, and agent-style workflows (OpenAI-style schemas).
Reasoning: Compatible with configurable reasoning effort (e.g. low / medium / high in system prompt) where the format is preserved; full chain-of-thought available for debugging and analysis.
Evaluated on coding and tool-heavy benchmarks (e.g. Tau2-bench, Terminal-Bench) alongside general intelligence benchmarks.

Tool Calling

HyperNova 60B 2605 supports native tool use and is well-suited for:

Function calling with defined schemas
Structured outputs
Coding-oriented tool workflows (e.g. browser tasks, code execution where supported)

The model can detect when to invoke tools, emit structured JSON tool calls, and consume tool outputs to continue generation. Tool-calling behavior follows OpenAI-style schemas; compatibility refers to format and structure—exact parity with the base or other models is not guaranteed. Compared with HyperNova 60B 2602, this release improves on coding and general evaluation tracks—including IFBench, Tau2-bench, Terminal Bench, and AA-LCR under the high-reasoning setup reported below.

Example Tool Call

{
  "name": "get_weather",
  "arguments": {
    "city": "Paris",
    "date": "2026-02-10"
  }
}

Architecture

Model Specifications

Specification	Value
Total parameters	60B, 4.8B active MoE

Evaluation & Benchmarks

Evaluation Methodology

Benchmark scores were obtained with the following setups. Methodology varies by benchmark family.

HLE, MMLU-Pro, AIME25, GPQA:d, LiveCodeBench

Evaluation framework: Nemo-skills
Inference library: vLLM 0.13.0
Hardware: 1× NVIDIA H200 Tensor Core GPU
Reasoning effort: high
Decoding: temperature = 0.6, max_tokens = 131072, top_p = 1.0, top_k = 0
Batch size: 64

IFBench, AA-LCR, SciCode

Evaluation framework: Nemo-skills
Inference library: vLLM 0.13.0
Hardware: 1× NVIDIA H200 Tensor Core GPU
Reasoning effort: high
Decoding: temperature = 1.0, max_tokens = 131072, top_p = 1.0, top_k = 0
Batch size: 64

Tau2-bench (Telecom)

Evaluation framework: EvalScope 1.4.1
Inference library: vLLM 0.13.0
Hardware: 1× NVIDIA H200 Tensor Core GPU
Reasoning effort: high (agent extra_body.reasoning_effort)
Decoding (agent): temperature = 1.0, top_p = 1.0, min_tokens = 1
Decoding (judge / user simulator): temperature = 0.7, timeout = 600
Reproducibility: subset telecom (default); max steps 100; repeats 3; tool-call parser openai (agent), hermes (judge)

Terminal-Bench Hard (Artificial Analysis subset):

Evaluation framework: laude-institute/harbor == 0.1.43
Inference library: vLLM == 0.13.0
Hardware: 1× NVIDIA H200 Tensor Core GPU
Reasoning effort: high
Decoding: temperature = 1.0, top_p = 1.0, max-model-len = 131072
Reproducibility: subset from AA (https://artificialanalysis.ai/methodology/intelligence-benchmarking#terminal-bench-hard)
Agent: terminus-2, max episodes 100; repeats 3;

Quantitative Results (Reported & Planned)

Benchmark	gpt-oss-120b	HyperNova 60B 2602	HyperNova 60B 2605
HLE	18.50	7.28	14.97
MMLU-Pro	79.64	74.25	76.77
Tau2-bench (Telecom)	63.74	60.53	61.70
AIME25	93.67	86.00	90.00
GPQA:d	74.64	65.56	71.92
IFBench	67.01	59.40	66.57
SciCode	41.52	33.53	36.00
LiveCodeBench	62.75	51.53	68.68
Terminal Bench	24.24	12.12	15.91
AA-LCR	49.00	35.67	40.33

Quantitative Results (Inference Performance)

Metrics reported

System Output Throughput (higher is better): Mean output tokens per second across all concurrent requests over the benchmarking phase.
End-to-End Latency per Query (lower is better): Median end-to-end response time for each query from the time the query is sent.
Output Speed per Query (higher is better): Median output tokens per second after the first token is received for each query.
Time to first token (TTFT) (lower is better): Median time to first token.
Estimated total memory — (lower is better): Median from each GuideLLM phase (estimated total footprint: weights plus KV contribution from monitored usage).
Model weights (lower is better):

On the same hardware and harness, HyperNova 60B 2605 is compared to gpt-oss-120b using GuideLLM. Each table lists median values for that model at each concurrency phase (1 → 256 concurrent requests).

gpt-oss-120b

Concurrency	Throughput (tok/s)	E2E latency (s)	Output speed (tok/s)	TTFT (s)	Est. total memory (GB)	Model weights (GB)
1	173	3.02	387.1	1.51	62.0	61.6
2	292	3.89	372.1	1.78	62.4	61.6
4	453	5.26	208.0	2.23	63.2	61.6
8	643	6.47	181.7	3.02	64.8	61.6
16	897	11.21	102.5	4.28	68.1	61.6
32	1114	15.51	75.1	6.25	74.6	61.6
64	1404	24.32	52.1	10.17	87.6	61.6
128	1828	42.99	28.3	18.23	114.0	61.6
192	1818	61.47	29.8	38.43	113.9	61.6
256	1842	81.04	29.5	57.45	114.0	61.6

HyperNova 60B 2605

Concurrency	Throughput (tok/s)	E2E latency (s)	Output speed (tok/s)	TTFT (s)	Est. total memory (GB)	Model weights (GB)
1	179	2.12	336.3	1.20	32.1	31.8
2	304	2.21	457.9	1.44	32.4	31.8
4	487	2.91	305.8	1.76	33.0	31.8
8	740	3.84	207.8	2.31	34.1	31.8
16	982	5.74	142.0	3.37	36.5	31.8
32	1233	8.46	101.7	5.25	41.1	31.8
64	1482	14.14	54.2	8.60	50.4	31.8
128	1923	25.03	32.0	15.09	69.0	31.8
192	1808	37.88	24.5	23.93	87.6	31.8
256	1716	52.16	18.8	31.89	106.5	31.8

Performance evaluation conditions

Our performance evaluation follows the spirit of Artificial Analysis.

Inference library: vLLM 0.13.0
Monitoring libraries: GuideLLM, nvidia-ml-py
Hardware: 1× NVIDIA H200 Tensor Core GPU
Conditions: concurrency phases 1, 2, 4, 8, 16, 32, 64, 128, 192, and 256 concurrent requests (one GuideLLM phase each)
Phase duration: Each phase lasts 3 minutes (excluding ramp-up and cool-down periods).
Workload shape: input length is ~1000 tokens per query (median); median output length varies by phase and model.
Streaming: Benchmarking is conducted with streaming enabled.

The figure below is a side-by-side comparison at concurrency = 128 only

Languages

Primary language: English
Other languages: Not formally evaluated

The model was trained primarily on English-language data. Performance on other languages may vary and has not been systematically measured.

Intended Use

Recommended Use Cases

Reasoning and analysis (with configurable reasoning effort where supported)
Tool-augmented applications, with emphasis on coding and general assistant use (function calling, web browsing, code execution, structured outputs)
Code generation and reasoning
Chatbots and virtual assistants
Retrieval-augmented generation (RAG)

Out-of-Scope Uses

Harmful, illegal, or deceptive content generation
Impersonation of real individuals without consent
High-risk decision-making without human oversight
Surveillance or tracking of individuals
Any use that violates applicable laws or regulations

Safety & Limitations

Known Limitations

English-centric training data.
Format: For best results, use the same harmony response format as gpt-oss-120b where applicable; behavior may differ otherwise.
Tool calling depends on correct schema and tool design; exact parity with gpt-oss-120b or other models is not guaranteed.

Recommendations

Validate tool outputs before execution
Use human oversight for critical applications
Perform task-specific evaluation prior to deployment

Model Information

Field	Value
Model name	HyperNova 60B 2605
Version	2605
Release date	26/02/2026
Developed by	Multiverse Computing
License	Apache 2.0
Contact	business@multiversecomputing.com

Citation

If you use this model, please cite the base model and this variant:

@misc{openai2025gptoss120b,
  title         = {gpt-oss-120b \& gpt-oss-20b Model Card},
  author        = {OpenAI},
  year          = {2025},
  eprint        = {2508.10925},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2508.10925}
}
@misc{hypernova60b2605,
  title = {HyperNova 60B 2605: Model developed based on gpt-oss-120b},
  author = {Multiverse Computing},
  year = {2026},
  url = {https://huggingface.co/MultiverseComputingCAI/HyperNova-60B-2605},
  note = {Model developed based on openai/gpt-oss-120b using CompactifAI technology}
}

Built by Multiverse Computing · Report an issue · Discord

Downloads last month: 339

Safetensors

Model size

59B params

Tensor type

BF16

Model tree for MultiverseComputingCAI/Hypernova-60B-2605

Base model

openai/gpt-oss-120b

Quantized

MultiverseComputingCAI/HyperNova-60B