This model was obtained by quantizing the weights of DeepSeek-R1-Distill-Llama-70B to INT4 data type. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%.

Only the weights of the linear operators within transformers blocks are quantized. Weights are quantized using a symmetric per-group scheme, with group size 128. The GPTQ algorithm is applied for quantization, as implemented in the llm-compressor library.

Use with vLLM

This model can be deployed efficiently using the vLLM backend, as shown in the example below.

python

from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

number_gpus = 1
model_name = "neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16"

tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)

messages_list = [
    [{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]

prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]

outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)

generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)

vLLM also supports OpenAI-compatible serving. See the documentation for more details.

Creation

This model was created with llm-compressor by running the code snippet below.

python

from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.compression.helpers import calculate_offload_device_map

# Load model
model_stub = "deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
model_name = model_stub.split("/")[-1]

num_samples = 3072
max_seq_len = 8192

tokenizer = AutoTokenizer.from_pretrained(model_stub)

device_map = calculate_offload_device_map(
    model_stub,
    reserve_for_hessians=True,
    num_gpus=2,
    torch_dtype="auto",
)

model = AutoModelForCausalLM.from_pretrained(
    model_stub,
    device_map=device_map,
    torch_dtype="auto",
)

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 scheme
recipe = QuantizationModifier(
    targets="Linear",
    scheme="W4A16",
    ignore=["lm_head"],
    dampening_frac=0.1,
)

# Apply quantization
oneshot(
    model=model,
    dataset=ds, 
    recipe=recipe,
    max_seq_length=max_seq_len,
    num_calibration_samples=num_samples,
)

# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w4a16
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")

Evaluation

The model was evaluated on OpenLLM Leaderboard V1 and V2, using the following commands:

OpenLLM Leaderboard V1:

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
  --tasks openllm \
  --write_out \
  --batch_size auto \
  --output_path output_dir \
  --show_config

OpenLLM Leaderboard V2:

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16",dtype=auto,max_model_len=4096,tensor_parallel_size=1,enable_chunked_prefill=True \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --tasks leaderboard \
  --write_out \
  --batch_size auto \
  --output_path output_dir \
  --show_config

Accuracy

Category	Metric	deepseek-ai/DeepSeek-R1-Distill-Llama-70B	neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16	Recovery
Reasoning	AIME 2024 (pass@1)	67.83	65.61	96.73%
MATH-500 (pass@1)	95.29	95.19	99.9%
GPQA Diamond (pass@1)	65.57	64.04	97.67%
Average Score	76.23	74.95	98.23%
OpenLLM V1	ARC-Challenge (Acc-Norm, 25-shot)	63.65	63.31	99.5%
GSM8K (Strict-Match, 5-shot)	93.03	93.03	100.0%
HellaSwag (Acc-Norm, 10-shot)	84.85	84.43	99.5%
MMLU (Acc, 5-shot)	78.04	77.15	98.9%
TruthfulQA (MC2, 0-shot)	56.67	57.79	102.0%
Winogrande (Acc, 5-shot)	78.22	79.48	101.6%
Average Score	75.74	75.86	100.2%
OpenLLM V2	IFEval (Inst Level Strict Acc, 0-shot)	42.45	42.41	99.9%
BBH (Acc-Norm, 3-shot)	21.26	16.96	79.8%
Math-Hard (Exact-Match, 4-shot)	0.00	0.00	---
GPQA (Acc-Norm, 0-shot)	9.51	6.68	---
MUSR (Acc-Norm, 0-shot)	14.87	12.91	---
MMLU-Pro (Acc, 5-shot)	4.27	2.38	---
Average Score	15.39	13.56	88.1%
Coding	HumanEval (pass@1)	81.10	80.20	98.9%
HumanEval (pass@10)	87.60	89.30	101.9%
HumanEval+ (pass@10)	75.20	73.00	97.1%
HumanEval+ (pass@10)	83.10	83.70	100.7%

Inference Performance

This model achieves up to 3.0x speedup in single-stream deployment and up to 2.6x speedup in multi-stream asynchronous deployment, depending on hardware and use-case scenario. The following performance benchmarks were conducted with vLLM version 0.7.2, and GuideLLM.

Benchmarking Command

guidellm --model neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_server

Single-stream performance (measured with vLLM version 0.7.2)

				Instruction Following 256 / 128	Multi-turn Chat 512 / 256	Docstring Generation 768 / 128	RAG 1024 / 128	Code Completion 256 / 1024	Code Fixing 1024 / 1024	Large Summarization 4096 / 512	Large RAG 10240 / 1536
GPU class	Number of GPUs	Model	Average cost reduction	Latency (s)	QPD	Latency (s)	QPD	Latency (s)	QPD	Latency (s)	QPD	Latency (s)	QPD	Latency (s)	QPD	Latency (s)	QPD	Latency (s)	QPD
A6000	4	deepseek-ai/DeepSeek-R1-Distill-Llama-70B	---	7.4	152	14.9	76	7.5	149	7.7	146	57.2	20	58.9	19	31.9	35	98.4	11
2	neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w8a8	1.93	7.7	292	15.2	148	7.8	287	8.0	282	60.7	37	60.2	37	32.3	70	104.0	22
2	neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16	2.83	4.9	457	10.0	225	5.5	411	5.8	389	38.9	58	39.2	57	23.7	95	76.6	29
A100	2	deepseek-ai/DeepSeek-R1-Distill-Llama-70B	---	6.4	157	12.8	79	6.6	153	6.7	151	50.4	20	50.8	20	27.0	37	85.4	12
2	neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w8a8	1.48	4.1	245	8.2	123	4.2	238	4.3	235	32.4	31	32.8	31	17.6	57	90.8	11
1	neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16	2.69	4.6	440	9.2	220	4.9	407	5.2	389	35.3	57	36.3	55	21.2	95	68.1	30
H100	2	deepseek-ai/DeepSeek-R1-Distill-Llama-70B	---	3.8	149	7.6	74	3.9	146	3.9	144	30.0	19	30.4	19	16.1	35	56.5	10
2	neuralmagic/DeepSeek-R1-Distill-Llama-70B-FP8-dynamic	1.39	2.7	210	5.3	106	2.7	207	2.8	203	21.1	27	21.4	26	11.5	49	47.2	12
1	neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16	1.83	4.0	277	7.9	138	4.1	266	4.2	262	31.2	35	31.8	34	17.8	61	61.4	18

**Use case profiles: prompt tokens / generation tokens

**QPD: Queries per dollar, based on on-demand cost at Lambda Labs (observed on 2/18/2025).

Multi-stream asynchronous performance (measured with vLLM version 0.7.2)

			Instruction Following 256 / 128	Multi-turn Chat 512 / 256	Docstring Generation 768 / 128	RAG 1024 / 128	Code Completion 256 / 1024	Code Fixing 1024 / 1024	Large Summarization 4096 / 512	Large RAG 10240 / 1536
Hardware	Model	Average cost reduction	Maximum throughput (QPS)	QPD	Maximum throughput (QPS)	QPD	Maximum throughput (QPS)	QPD	Maximum throughput (QPS)	QPD	Maximum throughput (QPS)	QPD	Maximum throughput (QPS)	QPD	Maximum throughput (QPS)	QPD	Maximum throughput (QPS)	QPD
A6000x4	deepseek-ai/DeepSeek-R1-Distill-Llama-70B	---	3.65	4102	1.56	1757	1.90	2143	1.48	1665	0.44	493	0.34	380	0.22	245	0.05	55
neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w8a8	1.76	5.89	6625	2.94	3307	3.36	3775	2.59	2916	0.74	828	0.53	601	0.35	398	0.11	120
neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16	1.48	4.91	5528	2.01	2259	2.03	2280	1.12	1255	1.11	1251	0.76	852	0.24	267	0.07	81
A100x4	deepseek-ai/DeepSeek-R1-Distill-Llama-70B	---	10.41	5235	5.10	2565	5.50	2766	4.36	2193	1.49	751	1.21	607	0.89	447	0.19	98
neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w8a8	1.63	18.11	9103	8.90	4477	9.41	4730	7.42	3731	2.44	1229	1.89	948	1.26	631	0.30	149
neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16	1.12	12.63	6353	5.32	2673	5.58	2804	4.27	2144	2.30	1158	1.45	729	0.76	381	0.22	110
H100x4	deepseek-ai/DeepSeek-R1-Distill-Llama-70B	---	14.04	2113	10.85	1634	12.25	1844	9.93	1494	3.68	554	2.82	425	1.81	273	0.35	52
neuralmagic/DeepSeek-R1-Distill-Llama-70B-FP8-dynamic	1.78	41.44	6236	19.64	2956	21.03	3166	16.72	2516	6.01	904	4.46	672	2.55	383	0.49	74
neuralmagic/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16	1.45	36.61	5509	15.12	2275	16.24	2443	13.22	1990	5.48	825	3.01	453	2.07	312	0.43	64

**Use case profiles: prompt tokens / generation tokens

**QPS: Queries per second.

**QPD: Queries per dollar, based on on-demand cost at Lambda Labs (observed on 2/18/2025).

RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16

DeepSeek-R1-Distill-Llama-70B-quantized.w4a16

Model Overview

Model Optimizations