Instructions to use Tech2wild/GLM-5.3-Int4-Int8Mix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tech2wild/GLM-5.3-Int4-Int8Mix with Transformers:

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

pipe = pipeline("text-generation", model="Tech2wild/GLM-5.3-Int4-Int8Mix")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tech2wild/GLM-5.3-Int4-Int8Mix")
model = AutoModelForCausalLM.from_pretrained("Tech2wild/GLM-5.3-Int4-Int8Mix", 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 Tech2wild/GLM-5.3-Int4-Int8Mix with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tech2wild/GLM-5.3-Int4-Int8Mix"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tech2wild/GLM-5.3-Int4-Int8Mix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Tech2wild/GLM-5.3-Int4-Int8Mix

SGLang

How to use Tech2wild/GLM-5.3-Int4-Int8Mix 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 "Tech2wild/GLM-5.3-Int4-Int8Mix" \
    --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": "Tech2wild/GLM-5.3-Int4-Int8Mix",
		"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 "Tech2wild/GLM-5.3-Int4-Int8Mix" \
        --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": "Tech2wild/GLM-5.3-Int4-Int8Mix",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Tech2wild/GLM-5.3-Int4-Int8Mix with Docker Model Runner:
```
docker model run hf.co/Tech2wild/GLM-5.3-Int4-Int8Mix
```

Tony DeAngelo commited on about 22 hours ago

Commit

206507b

verified ·

1 Parent(s): 04fc2bb

Card: weights live + public, benchmark table (46 tok/s c6), GitHub recipe link

Browse files

Files changed (1) hide show

README.md +11 -3

README.md CHANGED Viewed

@@ -22,8 +22,8 @@ tags:
 # GLM-5.3 Int4-Int8Mix (743B) — the quant that fits 4x NVIDIA DGX Spark
-> ### 🚧 Weights uploading — page staged (2026-08-28)
-> This card is live; the model shards are being quantized and will land here shortly. Everything below describes exactly what is being published. If a number is marked TBD it is being measured on our own hardware and will be filled in with a date next to it.
 An **Int4-Int8 mixed-precision** quantization of the full **[zai-org/GLM-5.3](https://huggingface.co/zai-org/GLM-5.3)** (743B total / ~40B active MoE, `glm5_next`, 78 layers, 1M context), in the **`compressed-tensors`** format for **vLLM**. Produced with the QuantTrio-style recipe (data-free, mixed W4A16 / W8A16), it is, as far as we can tell, the **first quant of the big GLM-5.3 that actually serves on four DGX Spark (GB10) nodes** with real KV-cache headroom.
@@ -75,9 +75,17 @@ Produced by a shard-streaming RTN quantizer (reads one BF16 shard at a time, qua
 - **Numerical round-trip:** int8 group/128 ≈ 0.70% rel error, int4 ≈ 12% (normal for 16 levels), full range used.
 - **Serves live:** TP4 across 4× DGX Spark (GB10/sm121), vLLM 0.23.1rc1, weights 95.53 GiB/rank, fp8_ds_mla KV, 202,944-token KV pool @ 200K ctx, health 200. Passed the bat-and-ball coherence trap ($0.05 with correct algebra) — a mis-quantized router or indexer cannot do that.
 **NOT yet done (honest):**
 - **No 69-scenario eval.** Coherence is proven; quality-vs-fp8 parity is NOT measured. Do not assume parity.
-- **Speed:** not benchmarked representatively. Any current number is thinking-ON, no spec-decode, no CUDA graphs = a FLOOR, not the model's real speed. Proper DFlash2 + graphs numbers will be added when measured.
 ## Credits (what's whose)

 # GLM-5.3 Int4-Int8Mix (743B) — the quant that fits 4x NVIDIA DGX Spark
+> ### ✅ Live — all 282 shards uploaded, fully open (2026-08-29)
+> The complete model is here: 282 safetensors shards + config + tokenizer, ~378 GB, **public and ungated**. Everything below is verified on our own hardware. Recipe + launchers + benchmarks: **[github.com/tonyd2wild/GLM-5.3-Int4-Int8Mix-TP4-4x-DGX-Spark](https://github.com/tonyd2wild/GLM-5.3-Int4-Int8Mix-TP4-4x-DGX-Spark)**.
 An **Int4-Int8 mixed-precision** quantization of the full **[zai-org/GLM-5.3](https://huggingface.co/zai-org/GLM-5.3)** (743B total / ~40B active MoE, `glm5_next`, 78 layers, 1M context), in the **`compressed-tensors`** format for **vLLM**. Produced with the QuantTrio-style recipe (data-free, mixed W4A16 / W8A16), it is, as far as we can tell, the **first quant of the big GLM-5.3 that actually serves on four DGX Spark (GB10) nodes** with real KV-cache headroom.
 - **Numerical round-trip:** int8 group/128 ≈ 0.70% rel error, int4 ≈ 12% (normal for 16 levels), full range used.
 - **Serves live:** TP4 across 4× DGX Spark (GB10/sm121), vLLM 0.23.1rc1, weights 95.53 GiB/rank, fp8_ds_mla KV, 202,944-token KV pool @ 200K ctx, health 200. Passed the bat-and-ball coherence trap ($0.05 with correct algebra) — a mis-quantized router or indexer cannot do that.
+**Performance (measured — TP4, 200K ctx, `fp8_ds_mla` KV, MTP k=4, thinking off, all four ranks clocking correctly):**
+| concurrency | 1 | 2 | 3 | 4 | 6 |
+|---|---|---|---|---|---|
+| **aggregate tok/s** | 12.12 | 21.71 | 28.30 | 33.11 | **46.03** |
+Single-stream is ~12 tok/s; **46 is the peak at 6 concurrent streams**. For reference, the GLM-5.2 QuantTrio recipe on the same four nodes reports 32.5 mean / 36 peak.
 **NOT yet done (honest):**
 - **No 69-scenario eval.** Coherence is proven; quality-vs-fp8 parity is NOT measured. Do not assume parity.
+- **DFlash2 speculative decode is not yet enabled** (native MTP is). It is one flag away (`fp8_e4m3` KV, method `dflash`, `num_speculative_tokens` 7) and is the next speed step.
 ## Credits (what's whose)