Instructions to use ubergarm/Qwen3-235B-A22B-Instruct-2507-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 ubergarm/Qwen3-235B-A22B-Instruct-2507-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 ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K

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 ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K

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 ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K

Use Docker

docker model run hf.co/ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ubergarm/Qwen3-235B-A22B-Instruct-2507-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": "ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K

Ollama
How to use ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF with Ollama:
```
ollama run hf.co/ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K
```

Unsloth Studio

How to use ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF 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 ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF 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 ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF to start chatting

How to use ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K

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": "ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF with Docker Model Runner:
```
docker model run hf.co/ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K
```

Lemonade

How to use ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K

Run and chat with the model

lemonade run user.Qwen3-235B-A22B-Instruct-2507-GGUF-Q2_K

List all available models

lemonade list

Hermes Agent

How to use ubergarm/Qwen3-235B-A22B-Instruct-2507-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 ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K

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 ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K

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 "ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF:Q2_K" \
  --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"

ubergarm commited on Jul 22, 2025

Commit

7cc02fa

1 Parent(s): 1283e26

Add IQ2_KL and graph

Browse files

Files changed (3) hide show

.gitattributes +1 -0
README.md +47 -0
images/perplexity.png +3 -0

.gitattributes CHANGED Viewed

@@ -35,4 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 imatrix-*.dat filter=lfs diff=lfs merge=lfs -text
 *.gguf filter=lfs diff=lfs merge=lfs -text
 imatrix-Qwen3-235B-A22B-Instruct-2507-BF16.dat filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 imatrix-*.dat filter=lfs diff=lfs merge=lfs -text
 *.gguf filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
 imatrix-Qwen3-235B-A22B-Instruct-2507-BF16.dat filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -28,6 +28,8 @@ Also thanks to all the folks in the quanting and inferencing community on [Beave
 ## Quant Collection
 Perplexity computed against *wiki.test.raw*. These first two are just test quants for baseline perplexity comparison:
 * `bf16` 437.989 GiB (16.003 BPW)
   - Final estimate: PPL = 4.3079 +/- 0.02544
 * `Q8_0` 232.769 GiB (8.505 BPW)
@@ -169,6 +171,51 @@ numactl -N 1 -m 1 \
 </details>
 ## Quick Start
 This example is for a single CUDA GPU hybrid infrencing with CPU/RAM. Check ik_llama.cpp discussions or my other quants for more examples for multi-GPU etc.

 ## Quant Collection
 Perplexity computed against *wiki.test.raw*. These first two are just test quants for baseline perplexity comparison:
+![Perplexity Chart](images/perplexity.png "Chart showing Perplexity improving as BPW increases.")
 * `bf16` 437.989 GiB (16.003 BPW)
   - Final estimate: PPL = 4.3079 +/- 0.02544
 * `Q8_0` 232.769 GiB (8.505 BPW)
 </details>
+## `IQ2_KL` 81.866 GiB (2.991 BPW)
+Final estimate: PPL = 4.7912 +/- 0.02910
+<details>
+<summary>👈 Secret Recipe</summary>
+```bash
+#!/usr/bin/env bash
+# Repeating Layers [0-93]
+custom="
+# Attention
+blk\..*\.attn_q.*=iq6_k
+blk\..*\.attn_k.*=q8_0
+blk\..*\.attn_v.*=q8_0
+blk\..*\.attn_output.*=iq6_k
+# Routed Experts
+blk\..*\.ffn_down_exps\.weight=iq3_ks
+blk\..*\.ffn_(gate|up)_exps\.weight=iq2_kl
+# Token Embedding
+token_embd\.weight=iq4_k
+output\.weight=iq6_k
+"
+custom=$(
+  echo "$custom" | grep -v '^#' | \
+  sed -Ez 's:\n+:,:g;s:,$::;s:^,::'
+)
+numactl -N 0 -m 0 \
+./build/bin/llama-quantize \
+    --custom-q "$custom" \
+    --imatrix /mnt/raid/models/ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF/imatrix-Qwen3-235B-A22B-Instruct-2507-BF16.dat \
+    /mnt/raid/models/ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF/Qwen3-235B-A22B-Instruct-2507-BF16-00001-of-00010.gguf \
+    /mnt/raid/models/ubergarm/Qwen3-235B-A22B-Instruct-2507-GGUF/Qwen3-235B-A22B-Instruct-2507-IQ2_KL.gguf \
+    IQ2_KL \
+    192
+```
+</details>
 ## Quick Start
 This example is for a single CUDA GPU hybrid infrencing with CPU/RAM. Check ik_llama.cpp discussions or my other quants for more examples for multi-GPU etc.

images/perplexity.png ADDED Viewed

Git LFS Details

SHA256: 41ecc117d176373aaa9aee060bbbb9383cbec9361385dbf71934596bed6ed537
Pointer size: 131 Bytes
Size of remote file: 134 kB