Instructions to use abenzerps/Nanbeige4.3-33B-GSQ-RCO-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 abenzerps/Nanbeige4.3-33B-GSQ-RCO-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 abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_M
# Run inference directly in the terminal:
llama cli -hf abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_M
# Run inference directly in the terminal:
llama cli -hf abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_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 abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_M

Use Docker

docker model run hf.co/abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_M

Llama new
LM Studio
Jan

vLLM

How to use abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abenzerps/Nanbeige4.3-33B-GSQ-RCO-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": "abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_M

Ollama
How to use abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF with Ollama:
```
ollama run hf.co/abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_M
```
Unsloth Desktop

How to use abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_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": "abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF with Docker Model Runner:
```
docker model run hf.co/abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_M
```

Lemonade

How to use abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_M

Run and chat with the model

lemonade run user.Nanbeige4.3-33B-GSQ-RCO-GGUF-IQ2_M

List all available models

lemonade list

Hermes Agent

How to use abenzerps/Nanbeige4.3-33B-GSQ-RCO-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 abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_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 abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_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 "abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_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"

abenzerps commited on 7 days ago

Commit

6afb30c

0 Parent(s):

feat: Add official Nanbeige4.3-33B GSQ-RCO quantizations (2.40 to 3.05 bpw)

Browse files

Files changed (7) hide show

.gitattributes +1 -0
Nanbeige4.3-33B-GSQ-RCO-IQ2_M.gguf +3 -0
Nanbeige4.3-33B-GSQ-RCO-IQ2_XS.gguf +3 -0
Nanbeige4.3-33B-GSQ-RCO-IQ2_XXS.gguf +3 -0
README.md +90 -0
SHA256SUMS.txt +3 -0
assets/benchmark.png +0 -0

.gitattributes ADDED Viewed

	@@ -0,0 +1 @@


1	+ *.gguf filter=lfs diff=lfs merge=lfs -text

Nanbeige4.3-33B-GSQ-RCO-IQ2_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6932af41332bf967cdf7a05c8456e7e9d3f63cbdb97f54465b63a8fe080bdd45
+size 12717026400

Nanbeige4.3-33B-GSQ-RCO-IQ2_XS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a206d1b670770466c76f9f64aabc1ffa8ae5c72c1e7c786175d8be751550a9ab
+size 10943548512

Nanbeige4.3-33B-GSQ-RCO-IQ2_XXS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a90d2ff1d0caba73ecc17f824e8ff89526e2b2ee289e8ddc1b000e109d83e1dc
+size 9902468192

README.md ADDED Viewed

	@@ -0,0 +1,90 @@

+---
+language:
+- en
+- zh
+license: apache-2.0
+library_name: gguf
+tags:
+- text-generation
+- gsq
+- rco
+- llama.cpp
+- quantized
+- reasoning
+- nanbeige
+- mixed-precision
+base_model: Nanbeige/Nanbeige4.3-33B
+base_model_relation: quantized
+pipeline_tag: text-generation
+---
+[![🤗 Model Requests](https://img.shields.io/badge/%F0%9F%A4%97_Model_Requests-Submit_Here-f59e0b?style=for-the-badge&labelColor=1f2937)](https://abenzerps.com/request-a-model/)
+> [!NOTE]
+> Active Release Status: Initial GSQ-RCO tiers (IQ2_XXS, IQ2_XS, IQ2_M) are live and verified. Higher tiers (IQ3_XS, IQ3_M, IQ4_XS, Q5_K_M) are currently in active calibration and quality verification.
+# Nanbeige4.3-33B GSQ-RCO GGUF
+Mixed-precision **GSQ-RCO** GGUF quantizations of [Nanbeige/Nanbeige4.3-33B](https://huggingface.co/Nanbeige/Nanbeige4.3-33B), optimized for efficient, high-fidelity local inference in `llama.cpp`.
+## Benchmark
+![Nanbeige4.3-33B Benchmark](https://huggingface.co/abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF/resolve/main/assets/benchmark.png)
+## GGUF Files
+| File | bpw | Size |
+| :--- | :---: | :---: |
+| [Nanbeige4.3-33B-GSQ-RCO-IQ2_XXS.gguf](Nanbeige4.3-33B-GSQ-RCO-IQ2_XXS.gguf) | 2.40 | 9.9 GB |
+| [Nanbeige4.3-33B-GSQ-RCO-IQ2_XS.gguf](Nanbeige4.3-33B-GSQ-RCO-IQ2_XS.gguf) | 2.65 | 10.9 GB |
+| **[Nanbeige4.3-33B-GSQ-RCO-IQ2_M.gguf](Nanbeige4.3-33B-GSQ-RCO-IQ2_M.gguf)** *(Recommended)* | **3.05** | **12.7 GB** |
+## Usage
+### llama.cpp
+**Interactive Chat**
+```bash
+llama-cli \
+  -m Nanbeige4.3-33B-GSQ-RCO-IQ2_M.gguf \
+  -ngl 99 \
+  -fa \
+  -b 2048 \
+  -c 16384 \
+  -cnv
+```
+**Local Server (OpenAI-Compatible)**
+```bash
+llama-server \
+  -m Nanbeige4.3-33B-GSQ-RCO-IQ2_M.gguf \
+  -ngl 99 \
+  -fa \
+  -b 2048 \
+  -c 32768 \
+  --port 8080
+```
+**64k Long-Context (Low-VRAM)**
+Using 4-bit KV cache (`-ctk q4_0 -ctv q4_0`) allows 65k context to run within **< 12 GB total VRAM** on consumer 12 GB GPUs (e.g. RTX 3060 12GB, RTX 4070):
+```bash
+llama-server \
+  -m Nanbeige4.3-33B-GSQ-RCO-IQ2_XXS.gguf \
+  -ngl 99 \
+  -fa \
+  -b 2048 \
+  -c 65536 \
+  -ctk q4_0 -ctv q4_0 \
+  --port 8080
+```
+### Ollama
+```bash
+ollama run hf.co/abenzerps/Nanbeige4.3-33B-GSQ-RCO-GGUF:IQ2_M
+```
+## Attribution & License
+- Distributed under the [Apache-2.0 License](LICENSE), matching upstream [Nanbeige/Nanbeige4.3-33B](https://huggingface.co/Nanbeige/Nanbeige4.3-33B).
+- Base model: [Nanbeige/Nanbeige4.3-33B](https://huggingface.co/Nanbeige/Nanbeige4.3-33B).

SHA256SUMS.txt ADDED Viewed

	@@ -0,0 +1,3 @@

+a90d2ff1d0caba73ecc17f824e8ff89526e2b2ee289e8ddc1b000e109d83e1dc  Nanbeige4.3-33B-GSQ-RCO-IQ2_XXS.gguf
+a206d1b670770466c76f9f64aabc1ffa8ae5c72c1e7c786175d8be751550a9ab  Nanbeige4.3-33B-GSQ-RCO-IQ2_XS.gguf
+6932af41332bf967cdf7a05c8456e7e9d3f63cbdb97f54465b63a8fe080bdd45  Nanbeige4.3-33B-GSQ-RCO-IQ2_M.gguf

assets/benchmark.png ADDED Viewed