Instructions to use Nishant2414/Qwen3.6-35B-A3B-TQ3_4S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nishant2414/Qwen3.6-35B-A3B-TQ3_4S with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Nishant2414/Qwen3.6-35B-A3B-TQ3_4S",
	filename="Qwen3.6-35B-A3B-TQ3_4S.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Nishant2414/Qwen3.6-35B-A3B-TQ3_4S with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16
# Run inference directly in the terminal:
llama-cli -hf Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16
# Run inference directly in the terminal:
llama-cli -hf Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16

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 Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16
# Run inference directly in the terminal:
./llama-cli -hf Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16

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 Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16

Use Docker

docker model run hf.co/Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16

LM Studio
Jan

vLLM

How to use Nishant2414/Qwen3.6-35B-A3B-TQ3_4S with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nishant2414/Qwen3.6-35B-A3B-TQ3_4S"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nishant2414/Qwen3.6-35B-A3B-TQ3_4S",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16

Ollama
How to use Nishant2414/Qwen3.6-35B-A3B-TQ3_4S with Ollama:
```
ollama run hf.co/Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16
```

Unsloth Studio

How to use Nishant2414/Qwen3.6-35B-A3B-TQ3_4S 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 Nishant2414/Qwen3.6-35B-A3B-TQ3_4S 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 Nishant2414/Qwen3.6-35B-A3B-TQ3_4S to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Nishant2414/Qwen3.6-35B-A3B-TQ3_4S to start chatting

How to use Nishant2414/Qwen3.6-35B-A3B-TQ3_4S with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16

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": "Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Nishant2414/Qwen3.6-35B-A3B-TQ3_4S with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16

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 Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Nishant2414/Qwen3.6-35B-A3B-TQ3_4S with Docker Model Runner:
```
docker model run hf.co/Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16
```

Lemonade

How to use Nishant2414/Qwen3.6-35B-A3B-TQ3_4S with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Nishant2414/Qwen3.6-35B-A3B-TQ3_4S:BF16

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-TQ3_4S-BF16

List all available models

lemonade list

Qwen3.6-35B-A3B-TQ3_4S

GGUF quantization of Qwen/Qwen3.6-35B-A3B using TQ3_4S with mixed-precision MoE compression — 2-bit experts, 4-bit attention.

Files

File	Description
`Qwen3.6-35B-A3B-TQ3_4S.gguf`	Main model (12.4 GiB, 3.07 BPW)
`mmproj-BF16.gguf`	Multimodal projector (BF16)

Quantization

MoE experts tolerate aggressive compression because only 8/256 are active per token. This quantization exploits that asymmetry:

Component	Quant	Rationale
Expert MLP gate/up	Q2_K	98% of params, MoE-tolerant
Expert MLP down	Q3_K	Write-back sensitivity
Attention Q/K/V/O	TQ3_4S	WHT-protected
Embeddings + output	Q6_K	Quality anchor

Runtime Requirement

This model requires the public TurboQuant runtime fork:

https://github.com/turbo-tan/llama.cpp-tq3

Recommended Settings (16GB VRAM)

./build/bin/llama-server \
  -m Qwen3.6-35B-A3B-TQ3_4S.gguf \
  -ngl 99 -c 4096 -np 1 \
  -ctk q4_0 -ctv tq3_0 -fa on \
  --jinja \
  --reasoning off --reasoning-budget 0 --reasoning-format deepseek

With vision:

./build/bin/llama-server \
  -m Qwen3.6-35B-A3B-TQ3_4S.gguf \
  --mmproj mmproj-BF16.gguf \
  -ngl 99 -c 4096 -np 1 \
  -ctk q4_0 -ctv tq3_0 -fa on \
  --jinja --no-mmproj-offload \
  --reasoning off --reasoning-budget 0 --reasoning-format deepseek

Performance (RTX 5060 Ti 16GB)

Metric	Value
PP512	1832 tok/s
TG128	107 tok/s
Size	12.4 GiB
BPW	3.07
ngl	99 (full GPU)

Fits entirely in 16GB VRAM — no CPU offload needed.

Quality

10/10 correct on standard QA benchmark (capital of France, 2+2, Python reverse string, gravity, WW2, primes, boiling point, Shakespeare, Jupiter, hello→Hola).

Base Model

Qwen/Qwen3.6-35B-A3B
Source: unsloth/Qwen3.6-35B-A3B-GGUF (Q8_0)

License

Apache 2.0 — same as the base model.

Tool Call Validation

Tested with --jinja on both --reasoning off and --reasoning on --reasoning-budget 2048:

Test	reasoning off	reasoning on
Basic tool call trigger	✅	✅
Tool response → final answer (no loop)	✅	✅
Correct tool selection from multiple	✅	✅
No tool call for simple questions	✅	✅
Multi-step tool use	✅	✅
Nested quote escaping retry (no loop)	✅	✅
Total	10/10	10/10

Recommended settings for tool-use / agentic workflows

--jinja --reasoning off --reasoning-budget 0 --reasoning-format deepseek

Avoid --presence-penalty above 0.5 for tool-use — high values diversify reasoning tokens but don't improve structured JSON output, and can cause repeated near-identical tool calls in agent loops.

If using --reasoning on, ensure your agent framework detects consecutive identical tool calls and breaks after 2-3 retries.

Run tests yourself

chmod +x test_tool_calls.sh
./test_tool_calls.sh 8085

Downloads last month: 63

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Nishant2414/Qwen3.6-35B-A3B-TQ3_4S

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

(459)

this model