Instructions to use AlexWortega/SIQ-1-35B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlexWortega/SIQ-1-35B with Transformers:

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

pipe = pipeline("text-generation", model="AlexWortega/SIQ-1-35B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("AlexWortega/SIQ-1-35B")
model = AutoModelForMultimodalLM.from_pretrained("AlexWortega/SIQ-1-35B")
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]:]))

llama-cpp-python

How to use AlexWortega/SIQ-1-35B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AlexWortega/SIQ-1-35B",
	filename="gguf/SIQ-1-35B.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use AlexWortega/SIQ-1-35B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AlexWortega/SIQ-1-35B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AlexWortega/SIQ-1-35B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AlexWortega/SIQ-1-35B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AlexWortega/SIQ-1-35B:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf AlexWortega/SIQ-1-35B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AlexWortega/SIQ-1-35B:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf AlexWortega/SIQ-1-35B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AlexWortega/SIQ-1-35B:Q4_K_M

Use Docker

docker model run hf.co/AlexWortega/SIQ-1-35B:Q4_K_M

LM Studio
Jan

vLLM

How to use AlexWortega/SIQ-1-35B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlexWortega/SIQ-1-35B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlexWortega/SIQ-1-35B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AlexWortega/SIQ-1-35B:Q4_K_M

SGLang

How to use AlexWortega/SIQ-1-35B 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 "AlexWortega/SIQ-1-35B" \
    --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": "AlexWortega/SIQ-1-35B",
		"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 "AlexWortega/SIQ-1-35B" \
        --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": "AlexWortega/SIQ-1-35B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use AlexWortega/SIQ-1-35B with Ollama:
```
ollama run hf.co/AlexWortega/SIQ-1-35B:Q4_K_M
```

Unsloth Studio

How to use AlexWortega/SIQ-1-35B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AlexWortega/SIQ-1-35B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AlexWortega/SIQ-1-35B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AlexWortega/SIQ-1-35B to start chatting

How to use AlexWortega/SIQ-1-35B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AlexWortega/SIQ-1-35B:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "AlexWortega/SIQ-1-35B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AlexWortega/SIQ-1-35B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AlexWortega/SIQ-1-35B:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default AlexWortega/SIQ-1-35B:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use AlexWortega/SIQ-1-35B with Docker Model Runner:
```
docker model run hf.co/AlexWortega/SIQ-1-35B:Q4_K_M
```

Lemonade

How to use AlexWortega/SIQ-1-35B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AlexWortega/SIQ-1-35B:Q4_K_M

Run and chat with the model

lemonade run user.SIQ-1-35B-Q4_K_M

List all available models

lemonade list

🤗 Model | 📦 GGUF | 📚 Dataset | 🪽 Demo

SIQ-1-tiny-35b 🪽

A tiny universal agent — autoresearch, coding, reasoning.

SIQ-1-tiny-35b is a tiny MoE — 35B total but only ~3B active per token — distilled to be a strong universal agent: equally at home running autonomous ML research (autoresearch), writing and debugging code, tool-use / agentic workflows, and hard reasoning. Despite its 3B active footprint it matches or beats much larger peers on core reasoning, sycophancy-resistance, and agentic coding — at a lower token cost.

Autoresearch duel (head-to-head)

In a controlled three-way autoresearch test on openai/parameter-golf — each model driving the same Pi-Agent edit train_gpt.py -> train (300s) -> eval val_bpb -> keep/revert loop on its own 1xA6000 for 2h — SIQ-1-tiny-35b reached val_bpb 1.767 (12 experiments, full 2h), neck-and-neck with Claude Opus 4.8 (~1.76) and far ahead of GLM-5.2 (2.078). GLM stagnated on the baseline — its only hypothesis was "add depth" (which hurt the metric) and it stopped emitting actions after ~65 min; SIQ instead climbed via LR-schedule and capacity edits (warmdown 1200->800, matrix_lr 0.04->0.05, ...). (val_bpb on a single A6000 is not comparable to the official 8xH100 leaderboard; this is the relative head-to-head under identical conditions.)

It is the winning arm of a controlled SFT / RFT / DPO / offline-GRPO post-training study on Qwen3.6-35B-A3B: ppo on the judge-top-half wins both ideation quality and agentic ability.

Performance

On the full 198-question GPQA-Diamond — all models served as Q4_K_M GGUF, greedy (temp 0), identical harness — SIQ-1-tiny-35b is Pareto-best: the highest accuracy and the fewest tokens (figure below). A 3B-active model edging out a full 35B base and Nex-N2-mini, while spending fewer tokens per question.

Benchmark	SIQ-1-tiny-35b	Nex-N2-mini	Qwen3.6-35B
General & Reasoning
GPQA-Diamond (Q4, co-measured)	70.2	67.2	68.2
GPQA-Diamond (bf16, full eval)	90.2	82.6	—
IFEval (inst-loose)	89.5	89.1	—
tok/question (GPQA, mean)	3158 ✅	3363	3500
Agentic coding
vibetest (Claude-judge, /10)	9.21	8.12	—
Ideation (autoresearch)
Opus-judge ideation (/100)	30.2	—	10.2 (base)

bf16 + tuned harness scores higher (90.2 GPQA); the Q4 row is the apples-to-apples co-measured comparison shown in the figure. Terminal-Bench 2.1 (Harbor, terminus-2, k=5) is in progress.

BullshitBench v2 — pushback vs. sycophancy

Score 0–2 (Clear Pushback = 2 / Partial = 1 / Accepted = 0). Panel: claude-sonnet-4.6 + gpt-5.2 + gemini-3.1-pro (mean), judge sees the final answer only (CoT stripped); no system prompt, temp 0.7.

model	avg /2	Clear Pushback	Partial	Accepted
SIQ-1-tiny-35b (high/think)	1.047	45	17	38
Nex-N2-Pro (free)	1.040	33	43	24

A tie on the mean, but different profiles: SIQ is polarized (cleanly exposes the BS 45× or fully buys it 38×); Nex hedges (rarely fully accepts, but rarely pushes back hard either — mostly Partial). Reference (official bullshit-benchmark, different panel, n=55, not co-measured): Opus 4.8 ≈ 1.96, GPT-5.5 ≈ 0.92.

Reasoning modes & system prompts

Qwen3-format hybrid reasoning, toggled per request via chat_template_kwargs.enable_thinking:

mode	toggle	behavior	use for
Thinking	`enable_thinking: true` (default)	emits `<think> … </think>`, then the answer	hard reasoning, math, agent planning
No-think	`enable_thinking: false`	answers directly	instruction-following, high-throughput

Reasoning effort is a trained control — Reasoning effort: low | medium | high in the system prompt scales the chain length (high for hard reasoning). For objective reasoning use greedy (temp 0) — it beats temp 0.7 by ~8 pts.

Copy-paste system prompts:

1 · Hard reasoning — greedy + high effort

Reasoning effort: high. Think step by step inside <think>...</think>, then give the final answer.

2 · Autoresearch ideator — propose a train.py edit to cut val_bpb

Reasoning effort: high. You are an autoresearch ideator.
Given the current train.py and its measured val_bpb under a fixed compute budget, propose ONE concrete,
high-impact edit that should reduce val_bpb. Reason inside <think>...</think>, then output:
- a one-line hypothesis,
- the edit as a minimal unified diff,
- the expected effect and how to verify it.

3 · Fast / instruction-following — no-think

(no system prompt; set enable_thinking=false — the model answers directly, no <think> block)

Usage

🪽 Try it now (no install): hosted ZeroGPU demo → AlexWortega/hermes-agent-zerogpu

llama.cpp (GGUF — single 48 GB GPU; Q4_K_M ≈ 21 GB)

These are the exact flags we serve with:

docker run -d --gpus all --network host -v /models:/m ghcr.io/ggml-org/llama.cpp:server-cuda \
  -m /m/SIQ-1-35B.Q4_K_M.gguf --alias SIQ-1-tiny-35b \
  -ngl 99 -c 131072 -np 4 --jinja --host 0.0.0.0 --port 8080

--jinja required (Qwen3 chat template → <think> + tool tags; enables enable_thinking).
-ngl 99 all layers on GPU; -c 131072 total context split across -np 4 slots (≈32k/slot — agentic loops need the headroom). Drop to -c 65536 if you only do short reasoning. OpenAI-compatible on :8080.

sglang (bf16 safetensors — e.g. 2× 48 GB)

python -m sglang.launch_server \
  --model-path AlexWortega/SIQ-1-35B \
  --tp 2 --context-length 131072 \
  --reasoning-parser qwen3 --tool-call-parser qwen3 \
  --host 0.0.0.0 --port 8080

Call it (OpenAI-compatible) — these are the params we run

from openai import OpenAI
client = OpenAI(base_url="http://localhost:8080/v1", api_key="x")
r = client.chat.completions.create(
    model="SIQ-1-tiny-35b",
    messages=[{"role": "system", "content": "Reasoning effort: high"},
              {"role": "user", "content": "..."}],
    temperature=0.0, top_p=0.95, top_k=40,                     # greedy (temp 0) for reasoning
    extra_body={"chat_template_kwargs": {"enable_thinking": True}})   # False → no-think

Sampling: reasoning → temperature 0 (greedy); general/creative → temp 0.7, top_p 0.95, top_k 40. Files: merged bf16 *.safetensors + GGUF Q4_K_M / Q5_K_M / Q8_0 (+ MTP f16).

Downloads last month: 40

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for AlexWortega/SIQ-1-35B

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

(140)

this model

AlexWortega
/

SIQ-1-35B