Instructions to use EchoLabs33/zamba2-7b-instruct-hxq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EchoLabs33/zamba2-7b-instruct-hxq with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="EchoLabs33/zamba2-7b-instruct-hxq")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EchoLabs33/zamba2-7b-instruct-hxq")
model = AutoModelForCausalLM.from_pretrained("EchoLabs33/zamba2-7b-instruct-hxq", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EchoLabs33/zamba2-7b-instruct-hxq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EchoLabs33/zamba2-7b-instruct-hxq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EchoLabs33/zamba2-7b-instruct-hxq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EchoLabs33/zamba2-7b-instruct-hxq

SGLang

How to use EchoLabs33/zamba2-7b-instruct-hxq with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "EchoLabs33/zamba2-7b-instruct-hxq" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EchoLabs33/zamba2-7b-instruct-hxq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "EchoLabs33/zamba2-7b-instruct-hxq" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EchoLabs33/zamba2-7b-instruct-hxq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EchoLabs33/zamba2-7b-instruct-hxq with Docker Model Runner:
```
docker model run hf.co/EchoLabs33/zamba2-7b-instruct-hxq
```

voidstream commited on Apr 3

Commit

80cde94

verified ·

1 Parent(s): ab85cea

Add RTX 4090 speed confirmation (1,827 tok/s), Mamba fast path install docs

Browse files

Files changed (1) hide show

README.md +23 -2

README.md CHANGED Viewed

@@ -71,6 +71,19 @@ All numbers from a single session, same GPU, same WikiText-2 test set (50 chunks
 | bnb 4-bit NF4 | 5.07 | 1,579 tok/s | 5,129 MB | 5,904 MB | 4 |
 | **HXQ 12-bit packed** | **5.02** | **1,764 tok/s** | **5,657 MB** | **6,511 MB** | **6** |
 ### Why HXQ wins
 - **Faster than dense** (1,764 vs 1,446 tok/s) -- fused Triton gather kernel eliminates memory bottleneck
@@ -114,7 +127,14 @@ outputs = model.generate(**inputs, max_new_tokens=32)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
-**Note:** Tested with `transformers>=4.49`. `mamba-ssm` and `causal-conv1d` recommended for fast Mamba2 inference.
 ## Codec Details
@@ -150,7 +170,8 @@ Zamba2-7B-Instruct is a hybrid architecture:
 ## Verification
-- **Benchmark receipt:** [`zamba2_7b_comparison.json`](https://huggingface.co/EchoLabs33/zamba2-7b-instruct-hxq/blob/main/zamba2_7b_comparison.json) -- RTX 3090, 2026-04-02
 - **Conversion receipt:** [`conversion_receipt.json`](https://huggingface.co/EchoLabs33/zamba2-7b-instruct-hxq/blob/main/conversion_receipt.json) -- Gate 1 PASS
 - **helix-substrate version:** 0.3.3 (12-bit packing, fused Triton gather)

 | bnb 4-bit NF4 | 5.07 | 1,579 tok/s | 5,129 MB | 5,904 MB | 4 |
 | **HXQ 12-bit packed** | **5.02** | **1,764 tok/s** | **5,657 MB** | **6,511 MB** | **6** |
+### Cross-GPU Confirmation (RTX 4090)
+| Method | Throughput | VRAM (load) | VRAM (peak) | GPU |
+|--------|------------|-------------|-------------|-----|
+| **HXQ 12-bit packed** | **1,827 tok/s** | **5,692 MB** | **6,886 MB** | RTX 4090 |
+Independently reproduced on 2026-04-03. Receipt: [`triton_gather_speed_4090_fast.json`](https://huggingface.co/EchoLabs33/zamba2-7b-instruct-hxq/blob/main/triton_gather_speed_4090_fast.json).
+**Profiled breakdown (512-token prefill):**
+- HelixLinear (gather + matmul): 43% of forward time
+- Mamba SSM + attention + norms: 57% of forward time
+- Per-layer overhead: 0.66ms avg (gather 0.21ms + cuBLAS 0.32ms)
 ### Why HXQ wins
 - **Faster than dense** (1,764 vs 1,446 tok/s) -- fused Triton gather kernel eliminates memory bottleneck
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```
+**Important:** Requires `mamba-ssm` and `causal-conv1d` for full speed. Without these, Mamba2 layers fall back to a naive implementation (~9x slower). Install from source:
+```bash
+pip install causal-conv1d
+pip install "mamba-ssm @ git+https://github.com/state-spaces/mamba.git@v2.2.2" --no-build-isolation
+```
+Tested with `transformers>=4.46,<5.0` and `helix-substrate>=0.3.3`.
 ## Codec Details
 ## Verification
+- **RTX 3090 benchmark:** [`zamba2_7b_comparison.json`](https://huggingface.co/EchoLabs33/zamba2-7b-instruct-hxq/blob/main/zamba2_7b_comparison.json) -- 1,764 tok/s, 2026-04-02
+- **RTX 4090 confirmation:** [`triton_gather_speed_4090_fast.json`](https://huggingface.co/EchoLabs33/zamba2-7b-instruct-hxq/blob/main/triton_gather_speed_4090_fast.json) -- 1,827 tok/s, 2026-04-03
 - **Conversion receipt:** [`conversion_receipt.json`](https://huggingface.co/EchoLabs33/zamba2-7b-instruct-hxq/blob/main/conversion_receipt.json) -- Gate 1 PASS
 - **helix-substrate version:** 0.3.3 (12-bit packing, fused Triton gather)