Qwen
ChatCodingAI codingReasoningMulti-purpose72.7B
Chat

Qwen 2.5 72B Instruct

Qwen · Qwen License

Top-tier 72B model, competitive with Llama 3.1 70B. Capable at coding and structured output. Requires 48 GB+ VRAM for usable quantizations.

Parameters
72.7B
Architecture
Dense
Context
131,072 tokens
Released
2024-09-19
Engines
llama.cpp, ollama, vLLM

Parameters

72.7B

VRAM

40.5 GB

Context

128K

Formats

3

GPUs

19

Qwen 2.5 72B Instruct (72.7B) requires 40.5 GB VRAM at recommended quality (Q4_K_M). On NVIDIA Grace Blackwell Ultra GB300, expect approximately 60 tok/s at Q4_K_M. For the best experience, High-End Home AI Server ($3,842) is recommended.

Source: OwnRig methodology

VRAM (Recommended)

40.5 GB

Quantization

Q4_K_M

File Size

36.4 GB

Max Context

128K tokens

Primary Use

Chat

Memory

VRAM Requirements

QualityQuantizationVRAMFile Size
efficientQ4_K_M40.5 GB36.4 GB
compressedQ3_K_M32.5 GB28.4 GB
compressedQ2_K25.3 GB21.8 GB
Scaling

Context Length Impact

KV cache VRAM at Q4_K_M quality. Longer context = more memory.

ContextKV CacheTotal VRAM
2K717 MB41.2 GBexceeds 24 GB
4K1.3 GB41.8 GBexceeds 24 GB
8K2.6 GB43.1 GBexceeds 24 GB
16K5.3 GB45.8 GBexceeds 24 GB
32K10.6 GB51.1 GBexceeds 24 GB
64K21.1 GB61.6 GBexceeds 24 GB
128K42.2 GB82.7 GBexceeds 24 GB

Compatible GPUs

19 devices
NVIDIA Grace Blackwell Ultra GB300Q4_K_M60 tok/sExcellent
Apple M4 Max (128GB Unified)Q4_K_M6 tok/sAcceptable
Apple M4 Max (64GB Unified)Q3_K_M6 tok/sAcceptable
Apple M4 Ultra (192GB)Q4_K_M9 tok/sAcceptable
AMD Radeon Pro W7900Q3_K_M6 tok/sAcceptable
NVIDIA RTX PRO 6000 BlackwellQ4_K_M26 tok/sAcceptable
NVIDIA RTX PRO 6000 Blackwell Max-QQ4_K_M24 tok/sAcceptable
AMD Radeon RX 7900 XTXQ2_K2 tok/sMarginal
Apple M3 Pro (18GB Unified)Q2_KNot viable
NVIDIA GeForce RTX 3080 10GBQ2_KNot viable
NVIDIA GeForce RTX 4060 8GBQ2_KNot viable
NVIDIA RTX 4060 Laptop (40-60W)Q2_KNot viable
NVIDIA RTX 4070 Laptop (80-115W)Q2_KNot viable
NVIDIA GeForce RTX 4070 Ti 12GBQ2_KNot viable
AMD Radeon RX 7600Q2_KNot viable
AMD Radeon RX 9070Q2_KNot viable
AMD Radeon RX 9060 XT 16GBQ2_KNot viable
AMD Radeon RX 9060 XT 8GBQ2_KNot viable
NVIDIA GeForce RTX 5060 8GBQ2_KNot viable

Showing 19 of 19 entries

Hardware

Recommended Builds

Complete PC builds that can run Qwen 2.5 72B Instruct.

FAQ

Frequently Asked Questions

How much VRAM does Qwen 2.5 72B Instruct need?
Qwen 2.5 72B Instruct requires 40.5 GB VRAM at recommended quality (Q4_K_M). At lower quality settings, it can fit in as little as 25.3 GB.
What is the best GPU for Qwen 2.5 72B Instruct?
The NVIDIA Grace Blackwell Ultra GB300 delivers the best performance for Qwen 2.5 72B Instruct, achieving 60 tok/s at Q4_K_M with an excellent rating.
What quantization should I use for Qwen 2.5 72B Instruct?
For the best quality, use Q4_K_M (40.5 GB VRAM). If your GPU has limited VRAM, Q2_K (25.3 GB) is the most efficient option with acceptable quality.
Is Qwen 2.5 72B Instruct good for coding?
Qwen 2.5 72B Instruct supports coding use cases. For the best coding experience, pair it with an embedding model for local RAG.

Related Guides

All models

Data confidence: verified. Source

VRAM requirements are calculated from model parameters and may vary by inference engine, context length, and batch size. Performance estimates are based on community benchmarks and should be verified for your specific configuration.Qwen is a trademark of its respective owner. OwnRig is not affiliated with or endorsed by the model creator.