Flexan/decompute-Nebula-S-v1-GGUF

GGUF Files for Nebula-S-v1

These are the GGUF files for decompute/Nebula-S-v1.

Downloads

GGUF Link	Quantization	Description
Download	Q2_K	Lowest quality
Download	Q3_K_S
Download	IQ3_S	Integer quant, preferable over Q3_K_S
Download	IQ3_M	Integer quant
Download	Q3_K_M
Download	Q3_K_L
Download	IQ4_XS	Integer quant
Download	Q4_K_S	Fast with good performance
Download	Q4_K_M	Recommended: Perfect mix of speed and performance
Download	Q5_K_S
Download	Q5_K_M
Download	Q6_K	Very good quality
Download	Q8_0	Best quality
Download	f16	Full precision, don't bother; use a quant

Note from Flexan

I provide GGUFs and quantizations of publicly available models that do not have a GGUF equivalent available yet, usually for models I deem interesting and wish to try out.

If there are some quants missing that you'd like me to add, you may request one in the community tab. If you want to request a public model to be converted, you can also request that in the community tab. If you have questions regarding this model, please refer to the original model repo.

You can find more info about me and what I do here.

Nebula-S-v1

Nebula-S-v1 is a reasoning-enhanced language model using the SVMS (Structured-Vector Multi-Stream) architecture.

Architecture

SVMS adds a multi-stream reasoning layer on top of a frozen 4B-parameter backbone:

• Structured Consistency: Topological constraint forcing cross-stream coherence
• Learned Router: Per-token stream weighting
• Delta Logits: Learnable correction to backbone predictions

Component	Details
Trainable	400M / 4.4B total

Quick Start

pip install torch transformers huggingface-hub

Option 1: Using huggingface_hub

from huggingface_hub import snapshot_download
import sys

snapshot_download("punitdecomp/Nebula-S-v1", local_dir="./Nebula-S-v1")
sys.path.insert(0, "./Nebula-S-v1")
from nebula_s import load_nebula_s

model, tokenizer = load_nebula_s("./Nebula-S-v1", device="cuda")

Option 2: Using git clone

git lfs install
git clone https://huggingface.co/punitdecomp/Nebula-S-v1

import sys
sys.path.insert(0, "./Nebula-S-v1")
from nebula_s import load_nebula_s

model, tokenizer = load_nebula_s("./Nebula-S-v1", device="cuda")

Generate a response

messages = [{"role": "user", "content": "Solve step by step: what is 17 * 23?"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to("cuda")
response = model.generate(
    inputs["input_ids"], inputs["attention_mask"],
    tokenizer, max_new_tokens=2048, temperature=0.7
)
print(response)

Training

• Data: Orca Math Word Problems (200K)
• Steps: 1000
• Method: Adapter-only (backbone frozen)

Evaluation Results

Nebula-S-v1 was evaluated on several challenging benchmarks:

Benchmark	Score
GSM8K	90%
GPQA	70.5%
HMMT (November 2025)	67%
MMLU-Pro	79.7%

These results demonstrate strong performance for a 4B-parameter model, particularly on math reasoning (GSM8K) and advanced knowledge/competition-level tasks.

License

Apache 2.0. Backbone derived from an Apache-2.0 licensed base model.