GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
sovthpaw
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
sovthpaw
Model Tree
Input Modalities
Output Modalities
Supported Functionality
OmniStep-new is a single bundled model that handles:
| Capability | How |
|---|---|
| Chat / instruction following | Qwen3-8B text backbone |
| Image + video understanding | Cosmos multimodal heads (built into the chat template as `< |
| Music generation (lyrics → music) | ACE-Step v1.5 turbo DiT + 1.7B LM + VAE, attached as modules |
| Tool / function calling | <tool_call> tags in chat template, supports OpenAI-style tool schemas |
| Long context | 40K native, YaRN-extendable to 256K+ |
It is not the agentic SFT variant — that's a separate LoRA on top. This is the base, ready for SFT warm-start or direct inference.
text
OmniStep-new (16GB F16 GGUF bundle)├─ Qwen3-8B text backbone (8.2B params, 36 layers, q_norm/k_norm)├─ Cosmos multimodal heads (vision encoder + projector)└─ ACE-Step music modules (1.7B LM + DiT v1.5 turbo + VAE)Built via Darwin Family weight-space merging (MRI-Trust Fusion) from:
nvidia/Cosmos3-Nano (text body extracted)Qwen/Qwen3-8B (gen-1 SFT-merged base)SouthpawIN/evolutionary-training/scripts/cosmos_qwen3_darwin_merge.py| File | Size | Notes |
|---|---|---|
OmniStep-new-F16.gguf | 16 GB | llama.cpp F16 single-file GGUF |
model-00001..7-of-7.safetensors | 16 GB | HF sharded safetensors |
config.json | <1 KB | Qwen3-compatible |
tokenizer.json / vocab.json / merges.txt | ~16 MB | Standard Qwen3 tokenizer + 26 multimodal/tool special tokens |
chat_template.json | ~5 KB | Tool-calling + vision/video/image_pad tokens |
bash
llama-server -m OmniStep-new-F16.gguf \ --host 127.0.0.1 --port 9080 \ -ngl 99 -c 262144 -fa on \ -ctk turbo4 -ctv turbo4 --no-mmappython
from transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("sovthpaw/omnistep-new")model = AutoModelForCausalLM.from_pretrained( "sovthpaw/omnistep-new", device_map="auto", torch_dtype="bfloat16",)out = model.generate(**tok("Hello, who are you?", return_tensors="pt").to("cuda"), max_new_tokens=200, do_sample=True, temperature=0.7)print(tok.decode(out[0]))python
import jsonfrom transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("sovthpaw/omnistep-new")model = AutoModelForCausalLM.from_pretrained("sovthpaw/omnistep-new", device_map="auto", torch_dtype="bfloat16") tools = [{ "name": "get_weather", "description": "Get current weather for a city", "parameters": {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]}}]msgs = [{"role": "user", "content": "What's the weather in Tokyo?"}]prompt = tok.apply_chat_template(msgs, tools=tools, add_generation_prompt=True, tokenize=False)out = model.generate(**tok(prompt, return_tensors="pt").to("cuda"), max_new_tokens=200)print(tok.decode(out[0][len(tok.encode(prompt)):]))# → <tool_call>{"name": "get_weather", "arguments": {"city": "Tokyo"}}</tool_call>This is gen 0. The roadmap:
SouthpawIN/evolutionary-trainingscripts/cosmos_qwen3_darwin_merge.pythe-omni-family.md — OmniStep = multimodal native + music + agentic backbone. This is the multimodal + music half; the agentic SFT is the LoRA adapter on top.TOWARDS SELF-IMPROVEMENT — Chris (via Nous Girl), 2026-06-22
OmniStep-new (16GB F16 GGUF bundle)├─ Qwen3-8B text backbone (8.2B params, 36 layers, q_norm/k_norm)├─ Cosmos multimodal heads (vision encoder + projector)└─ ACE-Step music modules (1.7B LM + DiT v1.5 turbo + VAE)llama-server -m OmniStep-new-F16.gguf \ --host 127.0.0.1 --port 9080 \ -ngl 99 -c 262144 -fa on \ -ctk turbo4 -ctv turbo4 --no-mmapfrom transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("sovthpaw/omnistep-new")model = AutoModelForCausalLM.from_pretrained( "sovthpaw/omnistep-new", device_map="auto", torch_dtype="bfloat16",)out = model.generate(**tok("Hello, who are you?", return_tensors="pt").to("cuda"), max_new_tokens=200, do_sample=True, temperature=0.7)print(tok.decode(out[0]))import jsonfrom transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("sovthpaw/omnistep-new")model = AutoModelForCausalLM.from_pretrained("sovthpaw/omnistep-new", device_map="auto", torch_dtype="bfloat16") tools = [{ "name": "get_weather", "description": "Get current weather for a city", "parameters": {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]}}]msgs = [{"role": "user", "content": "What's the weather in Tokyo?"}]prompt = tok.apply_chat_template(msgs, tools=tools, add_generation_prompt=True, tokenize=False)out = model.generate(**tok(prompt, return_tensors="pt").to("cuda"), max_new_tokens=200)print(tok.decode(out[0][len(tok.encode(prompt)):]))# → <tool_call>{"name": "get_weather", "arguments": {"city": "Tokyo"}}</tool_call>