Instructions to use hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF",
	filename="Qwen3-30B-A3B-Instruct-2507-asym-2bitexp.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 hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-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 hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF
# Run inference directly in the terminal:
llama cli -hf hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF
# Run inference directly in the terminal:
llama cli -hf hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-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 hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF
# Run inference directly in the terminal:
./llama-cli -hf hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-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 hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF

Use Docker

docker model run hf.co/hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF

LM Studio
Jan

vLLM

How to use hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-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": "hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF

Ollama
How to use hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF with Ollama:
```
ollama run hf.co/hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF
```

Unsloth Studio

How to use hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-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 hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-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 hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF to start chatting

How to use hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-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": "hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-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 hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-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 hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF with Docker Model Runner:
```
docker model run hf.co/hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF
```

Lemonade

How to use hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hyperspaceai/Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF

Run and chat with the model

lemonade run user.Qwen3-30B-A3B-Instruct-2507-asym-2bitexp-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

varunmathur commited on 8 days ago

Commit

b5ad90d

verified ·

1 Parent(s): 6c2eb2e

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +99 -0

README.md ADDED Viewed

	@@ -0,0 +1,99 @@

+---
+license: apache-2.0
+base_model: Qwen/Qwen3-30B-A3B-Instruct-2507
+base_model_relation: quantized
+tags:
+- gguf
+- qwen3moe
+- imatrix
+- asymmetric-quantization
+- 2-bit
+- moe
+pipeline_tag: text-generation
+---
+# Qwen3-30B-A3B-Instruct-2507 — Asymmetric 2-bit-Expert GGUF (imatrix)
+An **asymmetric, expert-aware** quantization of
+[Qwen/Qwen3-30B-A3B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507)
+(arch `qwen3moe`, 128 routed experts, 8 active per token, ~3B active params,
+48 layers).
+The idea (the "antirez" insight): in a routed-MoE model the bulk of the weights
+live in the expert FFNs, and most experts are only sparsely active. Push the
+routed experts to **2-bit** where the model is most redundant, keep the
+**attention and the embedding/output weights at higher precision** where error
+is most damaging, and steer the per-tensor bit-allocation with an **importance
+matrix (imatrix)**. The result fits comfortably in **16 GB** with only a modest
+perplexity cost versus the standard 4-bit baseline.
+## Asymmetric quantization scheme
+| Tensor group | Type | Count |
+|---|---|---|
+| Routed expert **gate** (`ffn_gate_exps`) | `IQ2_S` | 48 |
+| Routed expert **up** (`ffn_up_exps`)     | `IQ2_S` | 48 |
+| Routed expert **down** (`ffn_down_exps`) | `IQ3_S` | 48 |
+| Attention `q/k/v/output`                 | `Q4_K`  | 192 |
+| `token_embd`                             | `Q6_K`  | 1 |
+| `output` (lm_head)                       | `Q6_K`  | 1 |
+Notes:
+- **`down` experts get an extra bit (`IQ3_S`)** — they are more error-sensitive
+  than `gate`/`up`, so they are protected.
+- This architecture has **no shared expert** — all FFN experts are routed, so
+  there is no always-on expert to hold separately at high precision.
+- Quantization was guided by an **imatrix** computed over
+  `bartowski/calibration_datav3.txt` (128 chunks, ctx 512). `imatrix.dat` is
+  included in this repo.
+**Effective rate: 2.99 BPW**, on-disk **11.4 GB** (10.14 GiB).
+## Quality (perplexity, wikitext-2 raw test, 200 chunks @ ctx 512)
+| Model | PPL | Δ vs Q4_K_M |
+|---|---|---|
+| This asym 2-bit-expert (2.99 BPW, 11.4 GB) | **7.62** | +0.31 (+4.2%) |
+| Standard `Q4_K_M` (~4.8 BPW, 18.6 GB) | **7.32** | — |
+PPL measured with the same harness and chunk count for both. Lower is better.
+The asym build trades a small PPL increase for a **~38% smaller** file that
+clears the 16 GB bar.
+## 16 GB fit
+- Weights on disk / in VRAM: **11.4 GB**.
+- KV cache (48 layers, GQA `n_head_kv = 4`, `head_dim = 128`) at f16 is
+  ~0.092 MB/token, so a **16K-token** context adds ~**1.5 GB**.
+- 11.4 GB weights + ~1.5 GB KV (16K ctx) + runtime overhead ≈ **~14 GB < 16 GB**. ✅
+Use a quantized KV cache (`-ctk q8_0 -ctv q8_0`) to push context further.
+## Usage (llama.cpp)
+```bash
+# Instruct (non-thinking) variant — no <think> blocks.
+llama-server -m Qwen3-30B-A3B-Instruct-2507-asym-2bitexp.gguf -ngl 99 -c 16384
+```
+## Provenance / reproducibility
+- **Source:** `unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF` at `Q8_0`
+  (near-lossless) as the requantization source (`--allow-requantize`).
+- **imatrix corpus:** `bartowski/calibration_datav3.txt`, 128 chunks @ ctx 512.
+- **Tooling:** `llama-quantize` with repeatable `--tensor-type REGEX=TYPE`
+  overrides plus `--token-embedding-type Q6_K --output-tensor-type Q6_K`,
+  base type `IQ3_S`, imatrix-guided.
+```bash
+llama-quantize --allow-requantize --imatrix imatrix.dat \
+  --tensor-type "ffn_gate_exps=IQ2_S" --tensor-type "ffn_up_exps=IQ2_S" \
+  --tensor-type "ffn_down_exps=IQ3_S" \
+  --tensor-type "attn_q=Q4_K" --tensor-type "attn_k=Q4_K" \
+  --tensor-type "attn_v=Q4_K" --tensor-type "attn_output=Q4_K" \
+  --token-embedding-type Q6_K --output-tensor-type Q6_K \
+  src-Q8_0.gguf Qwen3-30B-A3B-Instruct-2507-asym-2bitexp.gguf IQ3_S
+```
+Coherence verified on a coding task (`merge_intervals`) and a chickens/rabbits
+reasoning problem (35 heads / 94 legs → 23 chickens, 12 rabbits).