Instructions to use Apexintelligence-AI/Apex-35B-V1.0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Apexintelligence-AI/Apex-35B-V1.0-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use Apexintelligence-AI/Apex-35B-V1.0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Apexintelligence-AI/Apex-35B-V1.0-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Apexintelligence-AI/Apex-35B-V1.0-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M

Ollama
How to use Apexintelligence-AI/Apex-35B-V1.0-GGUF with Ollama:
```
ollama run hf.co/Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Apexintelligence-AI/Apex-35B-V1.0-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Apexintelligence-AI/Apex-35B-V1.0-GGUF with Docker Model Runner:
```
docker model run hf.co/Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M
```

Lemonade

How to use Apexintelligence-AI/Apex-35B-V1.0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Apex-35B-V1.0-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Apexintelligence-AI/Apex-35B-V1.0-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Apexintelligence-AI/Apex-35B-V1.0-GGUF: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 Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Apexintelligence-AI/Apex-35B-V1.0-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Apexintelligence-AI/Apex-35B-V1.0-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Apex-35B-V1.0-GGUF

This repository contains GGUF builds of Apex-35B-V1.0 for llama.cpp, Unsloth, and other GGUF runtimes. For the model introduction, evaluation results, and serving with SGLang, vLLM, TokenSpeed, KTransformers, or Transformers, see the Apex-35B-V1.0 model card.

Model Overview

Developer: Apex Intelligence; built on Qwen3.6-35B-A3B
Number of parameters: 35B in total and 3B activated
Architecture: sparse mixture-of-experts, 40 layers, 3 Gated DeltaNet + 1 Gated Attention per 4 layers, 256 routed experts + 1 shared expert, 8 routed experts activated per token
Context length: 262,144 tokens, shared by input and output
Thinking: dynamic; the model decides on each turn whether to think and for how long
MTP: 1 MTP layer, included in every quantization (for BF16, in the second of the two split files)
Chat template: embedded in every quantization (for BF16, in the first split file); the generation prompt ends with <think>

Files

Quantization	File	Size	Notes
BF16	`Apex-35B-V1.0-BF16-00001-of-00002.gguf` `Apex-35B-V1.0-BF16-00002-of-00002.gguf`	71.1 GB	2 split files; pass the first file to llama.cpp
Q8_0	`Apex-35B-V1.0-Q8_0.gguf`	37.8 GB
Q6_K_L	`Apex-35B-V1.0-Q6_K_L.gguf`	32.8 GB
Q6_K_S	`Apex-35B-V1.0-Q6_K_S.gguf`	29.9 GB
Q6_K	`Apex-35B-V1.0-Q6_K.gguf`	29.2 GB
Q5_K_S	`Apex-35B-V1.0-Q5_K_S.gguf`	25.6 GB
Q5_K_M	`Apex-35B-V1.0-Q5_K_M.gguf`	25.3 GB
Q4_K_L	`Apex-35B-V1.0-Q4_K_L.gguf`	24.6 GB
IQ4_NL	`Apex-35B-V1.0-IQ4_NL.gguf`	22.8 GB
Q4_1	`Apex-35B-V1.0-Q4_1.gguf`	22.4 GB
Q4_K_M	`Apex-35B-V1.0-Q4_K_M.gguf`	21.7 GB
Q4_K_S	`Apex-35B-V1.0-Q4_K_S.gguf`	21.4 GB
Q4_0	`Apex-35B-V1.0-Q4_0.gguf`	20.4 GB
IQ4_XS	`Apex-35B-V1.0-IQ4_XS.gguf`	20.4 GB
MXFP4_MOE	`Apex-35B-V1.0-MXFP4_MOE.gguf`	20.3 GB
IQ3_M	`Apex-35B-V1.0-IQ3_M.gguf`	19.4 GB
Q3_K_L	`Apex-35B-V1.0-Q3_K_L.gguf`	18.7 GB
IQ3_S	`Apex-35B-V1.0-IQ3_S.gguf`	18.1 GB
Q3_K_M	`Apex-35B-V1.0-Q3_K_M.gguf`	17.8 GB
IQ3_XS	`Apex-35B-V1.0-IQ3_XS.gguf`	16.8 GB
Q3_K_S	`Apex-35B-V1.0-Q3_K_S.gguf`	16.8 GB
IQ3_XXS	`Apex-35B-V1.0-IQ3_XXS.gguf`	16.1 GB
Q2_K	`Apex-35B-V1.0-Q2_K.gguf`	14.3 GB
IQ2_M	`Apex-35B-V1.0-IQ2_M.gguf`	13.7 GB
IQ2_S	`Apex-35B-V1.0-IQ2_S.gguf`	12.5 GB
IQ2_XS	`Apex-35B-V1.0-IQ2_XS.gguf`	11.7 GB
IQ2_XXS	`Apex-35B-V1.0-IQ2_XXS.gguf`	11.3 GB
IQ1_M	`Apex-35B-V1.0-IQ1_M.gguf`	9.9 GB
IQ1_S	`Apex-35B-V1.0-IQ1_S.gguf`	9.0 GB

All files except BF16, Q8_0, Q6_K, Q5_K_M, and Q4_K_M were made with an importance matrix (imatrix), using the calibration data and the per-tensor layout method published by bartowski.

Quickstart

llama.cpp

Build llama.cpp from a recent master (NVIDIA GPU shown; see its build guide for other platforms):

git clone https://github.com/ggml-org/llama.cpp
cmake llama.cpp -B llama.cpp/build -DGGML_CUDA=ON
cmake --build llama.cpp/build --config Release -j --target llama-server llama-cli

Download one file, for example Q4_K_M:

hf download Apexintelligence-AI/Apex-35B-V1.0-GGUF Apex-35B-V1.0-Q4_K_M.gguf --local-dir .

Start an OpenAI-compatible server at http://localhost:8000/v1:

./llama.cpp/build/bin/llama-server -m Apex-35B-V1.0-Q4_K_M.gguf --jinja -ngl 99 -c 32768 --port 8000 --temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.0

--jinja is required: it applies the chat template embedded in the file.
The server returns the thinking in reasoning_content and converts tool calls into standard tool_calls.
llama-server keeps the thinking of earlier turns by default. Add --no-reasoning-preserve to keep only the thinking after the latest user message.
-c sets the context for the prompt and the output together (up to 262,144). With -c 32768, a long thinking can be cut off before the 65,536-token budget of the main card's examples; raise -c if you have the memory.

Unsloth

Install Unsloth and serve a downloaded file:

curl -fsSL https://unsloth.ai/install.sh | UNSLOTH_SKIP_AUTOSTART=1 sh
source ~/.profile   # or open a new shell, so that `unsloth` is on PATH
unsloth run --model Apex-35B-V1.0-Q4_K_M.gguf --parallel 1 --temperature 1.0 --top-p 0.95 --top-k 20 --min-p 0.0 --host 127.0.0.1 --port 8001

UNSLOTH_SKIP_AUTOSTART=1 stops the installer from starting Unsloth Studio in the foreground. The installer took 2 to 25 minutes in our tests. On its first start, unsloth run creates a local Unsloth Studio admin account (user name unsloth); its initial password is in ~/.unsloth/studio/auth/.bootstrap_password. Use the API key that Unsloth prints at startup as the bearer token, for example export OPENAI_BASE_URL="http://127.0.0.1:8001/v1" and export OPENAI_API_KEY="<key printed by unsloth run>".
Unsloth enables its own server-side tools (for example web search and code execution) by default. To send only your own messages and tools, add "enable_tools": false to each request (with the OpenAI SDK: extra_body={"enable_tools": False}).
Unsloth manages the served model name; do not pass --alias.
unsloth run keeps only the thinking after the latest user message by default. To keep the thinking of earlier turns, pass extra_body={"chat_template_kwargs": {"preserve_thinking": True}} as in the main card's examples.

Usage

Set model in the requests to the model ID that the server lists at /v1/models (unsloth run uses the file name, for example Apex-35B-V1.0-Q4_K_M). Otherwise use the same requests as for the BF16 model: see Using Apex-35B-V1.0 via the Chat Completions API. We recommend temperature=1.0, top_p=0.95, top_k=20, and an output budget large enough for the thinking. For multi-turn conversations and tool calls, append the complete assistant message, including reasoning_content and tool_calls, to messages.

License

Apex-35B-V1.0, including these GGUF files, is licensed under the Apache License 2.0.

Contact

If you have any questions, please reach out at contact@apexin.ai.

Downloads last month: 8,507

GGUF

Model size

36B params

Architecture

qwen35moe

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for Apexintelligence-AI/Apex-35B-V1.0-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

Apexintelligence-AI/Apex-35B-V1.0

Quantized

(9)

this model