No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from RedHatAI/Qwen3-4B-Instruct-2507-quantized.w8a8
All models by RedHatAI →This model was obtained by quantizing the weights of Qwen/Qwen3-4B-Instruct-2507 to INT8 data type. This optimization reduces the number of bits used to represent weights and activations from 16 to 8, reducing GPU memory requirements (by approximately 50%) and increasing matrix-multiply compute throughput (by approximately 2x). Weight quantization also reduces disk size requirements by approximately 50%.
Only weights and activations of the linear operators within transformers blocks are quantized. Weights are quantized with a symmetric static per-channel scheme, whereas activations are quantized with a symmetric dynamic per-token scheme. A combination of the SmoothQuant and GPTQ algorithms is applied for quantization, as implemented in the llm-compressor library.
This model can be deployed efficiently using the vLLM backend, as shown in the example below.
vLLM aslo supports OpenAI-compatible serving. See the documentation for more details.
The model was evaluated on the ifeval, mmlu_pro and gsm8k_platinum using lm-evaluation-harness, on reasoning tasks using lighteval. vLLM was used for all evaluations.
Deploy using vllm to create an OpenAI-compatible API endpoint:
vLLM:
lm-evaluation-harness
lighteval
lighteval_model_arguments.yaml
from vllm import LLM, SamplingParamsfrom transformers import AutoTokenizer
model_id = "RedHatAI/Qwen3-4B-Instruct-2507.w8a8"number_gpus = 1sampling_params = SamplingParams(temperature=0.6, top_p=0.95, top_k=20, min_p=0, max_tokens=256)
messages = [ {"role": "user", "content": prompt}]
tokenizer = AutoTokenizer.from_pretrained(model_id)
messages = [{"role": "user", "content": "Give me a short introduction to large language model."}]
prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
llm = LLM(model=model_id, tensor_parallel_size=number_gpus)
outputs = llm.generate(prompts, sampling_params)
generated_text = outputs[0].outputs[0].textprint(generated_text)from llmcompressor.modifiers.quantization import GPTQModifierfrom llmcompressor.modifiers.smoothquant import SmoothQuantModifierfrom llmcompressor.transformers import oneshotfrom transformers import AutoModelForCausalLM, AutoTokenizer
# Load modelmodel_stub = "Qwen/Qwen3-4B-Instruct"model_name = model_stub.split("/")[-1]
num_samples = 1024max_seq_len = 8192
model = AutoModelForCausalLM.from_pretrained(model_stub)
tokenizer = AutoTokenizer.from_pretrained(model_stub)
def preprocess_fn(example): return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}
ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")ds = ds.map(preprocess_fn)
# Configure the quantization algorithm and schemerecipe = [ SmoothQuantModifier( smoothing_strength=0.9, mappings=[ [["re:.*q_proj", "re:.*k_proj", "re:.*v_proj"], "re:.*input_layernorm"], ], ), GPTQModifier( ignore: ["lm_head"] config_groups={"group_0": {"targets": ["Linear"], "weights": { "num_bits": 4, "type": int, "strategy": "group", "group_size": 128, "symmetric": true, "dynamic": false, "observer": "mse" } } }, dampening_frac=0.1, )]
# Apply quantizationoneshot( model=model, dataset=ds, recipe=recipe, max_seq_length=max_seq_len, num_calibration_samples=num_samples,)
# Save to disk in compressed-tensors formatsave_path = model_name + "-quantized.w8a8"model.save_pretrained(save_path)tokenizer.save_pretrained(save_path)print(f"Model and tokenizer saved to: {save_path}")vllm serve RedHatAI/Qwen3-4B-Instruct-2507.w8a8 --max-model-len 262144lm_eval --model local-chat-completions \ --tasks mmlu_pro_chat \ --model_args "model=RedHatAI/Qwen3-4B-Instruct-2507.w8a8,max_length=262144,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=64,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=1200" \ --num_fewshot 0 \ --apply_chat_template \ --gen_kwargs "do_sample=True,temperature=0.6,top_p=0.95,top_k=20,min_p=0.0,max_gen_toks=64000lm_eval --model local-chat-completions \ --tasks ifeval \ --model_args "model=RedHatAI/Qwen3-4B-Instruct-2507.w8a8,max_length=262144,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=64,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=1200" \ --num_fewshot 0 \ --apply_chat_template \ --gen_kwargs "do_sample=True,temperature=0.6,top_p=0.95,top_k=20,min_p=0.0,max_gen_toks=64000lm_eval --model local-chat-completions \ --tasks mmlu_cot_llama \ --model_args "model=RedHatAI/Qwen3-4B-Instruct-2507.w8a8,max_length=262144,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=64,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=1200" \ --num_fewshot 0 \ --apply_chat_template \ --gen_kwargs "do_sample=True,temperature=0.6,top_p=0.95,top_k=20,min_p=0.0,max_gen_toks=64000lm_eval --model local-chat-completions \ --tasks gsm8k_platinum_cot_llama \ --model_args "model=RedHatAI/Qwen3-4B-Instruct-2507.w8a8,max_length=262144,base_url=http://0.0.0.0:8000/v1/chat/completions,num_concurrent=64,max_retries=3,tokenized_requests=False,tokenizer_backend=None,timeout=1200" \ --num_fewshot 0 \ --apply_chat_template \ --gen_kwargs "do_sample=True,temperature=0.6,top_p=0.95,top_k=20,min_p=0.0,max_gen_toks=64000model_parameters: model_name: RedHatAI/Qwen3-4B-Instruct-2507.w8a8 dtype: auto gpu_memory_utilization: 0.9 max_model_length: 40960 generation_parameters: temperature: 0.6 top_k: 20 min_p: 0.0 top_p: 0.95 max_new_tokens: 32000lighteval endpoint litellm lighteval_model_arguments.yaml \ "aime25|0,math_500|0,gpqa:diamond|0"