Instructions to use peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF",
	filename="SR2AM-v1.0-30B-IQ2XXS-asym.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 peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-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 peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF
# Run inference directly in the terminal:
llama cli -hf peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF
# Run inference directly in the terminal:
llama cli -hf peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF

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 peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF
# Run inference directly in the terminal:
./llama-cli -hf peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF

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 peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF

Use Docker

docker model run hf.co/peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF

LM Studio
Jan

vLLM

How to use peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-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": "peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF

Ollama
How to use peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF with Ollama:
```
ollama run hf.co/peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF
```

Unsloth Studio

How to use peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-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 peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-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 peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF to start chatting

How to use peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF

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": "peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-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 peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF

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 peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF

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 "peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF" \
  --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"

Docker Model Runner
How to use peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF with Docker Model Runner:
```
docker model run hf.co/peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF
```

Lemonade

How to use peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF

Run and chat with the model

lemonade run user.SR2AM-v1.0-30B-IQ2XXS-asym-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

SR2AM-v1.0-30B — Asymmetric IQ2_XXS/Q2_K GGUF

Asymmetric quantization of sailing-lab/SR2AM-v1.0-30B (Qwen3-MoE, 48 layers, 128 experts, top-8) using the strategy popularized by antirez/ds4: aggressively quantize the bulky routed-expert FFN tensors and keep the rest at higher precision so the whole model fits on a 24 GB consumer GPU at full speed.

Quantization recipe

Tensor family	Type
`ffn_up_exps.weight` (routed)	IQ2_XXS
`ffn_gate_exps.weight` (routed)	IQ2_XXS
`ffn_down_exps.weight` (routed)	Q2_K
attention proj (`attn_q/k/v/output`)	Q6_K
shared/non-expert FFN, norms, router	Q6_K
`token_embd.weight`	Q8_0
`output.weight`	Q6_K

Imatrix calibration: 100 chunks × 512 tokens from bartowski calibration_datav3.

Tool: llama.cpp llama-quantize with --imatrix + --tensor-type overrides.

File

File	Size	BPW
`SR2AM-v1.0-30B-IQ2XXS-asym.gguf`	8.9 GB	2.50

vs. source BF16 GGUF (58.3 GB, 16.01 BPW) → 6.5× compression.

Runtime (RTX 3090 24 GB, full GPU offload)

Setting	Value
VRAM (with 40k ctx)	13.9 GB / 24 GB
Prefill	420.6 t/s
Decode	168.3 t/s

Quality

Benchmark	Score	Notes
MATH500 (subset N=30)	24/30 = 80.0 %	Qwen-spec sampling (see below). 0 truncations at the run config.

Comparable to published Qwen3-30B-A3B-Thinking-2507 BF16 numbers on MATH500 (~85–90 %); ~5–10 point delta at 2.50 BPW is in line with what asymmetric MoE quants achieve on reasoning benchmarks.

Usage

This is a thinking-mode model. Use generous output budgets and Qwen3 official sampling, otherwise reasoning chains get truncated and the model emits empty content.

llama-server \
  -m SR2AM-v1.0-30B-IQ2XXS-asym.gguf \
  -ngl 99 \
  -c 40960 \
  --jinja

Request body for evals / hard reasoning prompts:

{
  "messages": [...],
  "max_tokens": 32768,
  "temperature": 0.6,
  "top_p": 0.95,
  "top_k": 20,
  "min_p": 0.0,
  "presence_penalty": 1.0
}

Use a recent llama.cpp build with IQ2_XXS CUDA kernels (tested on b9124).

⚠️ Do not set temperature=0 — off-spec for Qwen3 thinking models and triggers degenerate long chains. Do not rely on chat_template_kwargs.enable_thinking=false — broken in current llama.cpp (#20182, #13189).

Credits

Base model: sailing-lab/SR2AM-v1.0-30B
Asymmetric-quant strategy: antirez/ds4
Calibration data: bartowski1182
Tooling: llama.cpp

Downloads last month: 26

GGUF

Model size

31B params

Architecture

qwen3moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for peppi314/SR2AM-v1.0-30B-IQ2XXS-asym-GGUF

Base model

Qwen/Qwen3-30B-A3B-Thinking-2507

Finetuned

sailing-lab/SR2AM-v1.0-30B

Quantized

(3)

this model