NelsaHost
search Login

Can I run Qwen 2.5 72B (Q4_K_M (GGUF 4-bit)) on NVIDIA A100 80GB?

check_circle
Perfect
Yes, you can run this model!
GPU VRAM
80.0GB
Required
36.0GB
Headroom
+44.0GB

VRAM Usage

0GB 45% used 80.0GB

Performance Estimate

Tokens/sec ~31.0
Batch size 3
Context 131072K

info Technical Analysis

NVIDIA A100 80GB provides excellent compatibility with Qwen 2.5 72B (72.00B). With 80.0GB of VRAM and only 36.0GB required, you have 44.0GB of headroom for comfortable inference. This allows for extended context lengths, batch processing, and smooth operation.

lightbulb Recommendation

You can run Qwen 2.5 72B (72.00B) on NVIDIA A100 80GB without any compromises. Consider using full context length and larger batch sizes for optimal throughput.

tune Recommended Settings

Batch_Size
3
Context_Length
131072
Inference_Framework
llama.cpp or vLLM

help Frequently Asked Questions

Can I run Qwen 2.5 72B (72.00B) on NVIDIA A100 80GB? expand_more
NVIDIA A100 80GB has 80.0GB VRAM, which provides 44.0GB of headroom beyond the 36.0GB required by Qwen 2.5 72B (72.00B). This is plenty of room for comfortable inference with room for KV cache, batching, and extended context lengths.
How much VRAM does Qwen 2.5 72B (72.00B) need? expand_more
Qwen 2.5 72B (72.00B) requires approximately 36.0GB of VRAM.
What performance can I expect? expand_more
Estimated 31 tokens per second.

GPU

memory
NVIDIA A100 80GB
80.0GB VRAM

AI Model

smart_toy
Qwen 2.5 72B (72.00B)
72.00B params

Alternative Quantizations

q3_k_m Perfect INT8 (8-bit Integer) Perfect

More with A100 80GB

Qwen 2.5 7B Perfect Qwen 2.5 7B Perfect Qwen 2.5 7B Perfect Qwen 2.5 7B Perfect