TokenAssemble

Alibaba/Qwen · open-weights model

Qwen2.5-72B-Instruct

Qwen2.5-72B-Instruct is a 72.7B-parameter model by Alibaba/Qwen. Its smallest quant (Q4_K_M) needs at least 50.7GB of GPU-addressable memory at 8K context; it loads cleanly at a quality quant on 7 of the 50 machines we track.

Parameters
72.7B
Layers
80
Max context
32K
Attention
GQA
License
apache-2.0

Config from Qwen/Qwen2.5-72B-Instruct

Quants and what they need

Measured file sizes; “needs” = weights + KV cache at 8K context + overhead.

QuantFile sizeNeeds ≥
Q8_077.3 GB80.6 GB
Q6_K64.3 GB67.7 GB
Q5_K_M54.5 GB57.8 GB
Q4_K_M47.4 GB50.7 GB

What runs Qwen2.5-72B-Instruct

Every machine we track, graded at its best clean-fit quant.

HardwareBest-quant verdict · llama.cpp · 8K context
Intel Arc A770 16 GBTight · C · Q4_K_Mpainful · offloadbeta
Intel Arc B580Tight · C · Q4_K_Mpainful · offloadbeta
AMD Radeon PRO W7900Tight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 3060 12 GBTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 3070Tight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 3070 TiTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 3080 10 GBTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 3080 12 GBTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 3080 TiTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 3090Tight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 3090 TiTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4060Tight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4060 Ti 16 GBTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4060 Ti 8 GBTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4070Tight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4070 SUPERTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4070 TiTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4070 Ti SUPERTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4080Tight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4080 SUPERTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 4090Tight · C · Q4_K_Mpainful · offloadbeta
NVIDIA RTX 5000 Ada GenerationTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 5060 Ti 16 GBTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 5070Tight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 5070 TiTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 5080Tight · C · Q4_K_Mpainful · offloadbeta
NVIDIA GeForce RTX 5090Tight · C · Q4_K_Musable · offloadbeta
NVIDIA RTX 6000 Ada GenerationTight · C · Q4_K_Mpainful · offloadbeta
NVIDIA RTX A6000Tight · C · Q4_K_Mpainful · offloadbeta
AMD Radeon RX 6800Tight · C · Q4_K_Mpainful · offloadbeta
AMD Radeon RX 6900 XTTight · C · Q4_K_Mpainful · offloadbeta
AMD Radeon RX 7800 XTTight · C · Q4_K_Mpainful · offloadbeta
AMD Radeon RX 7900 XTTight · C · Q4_K_Mpainful · offloadbeta
AMD Radeon RX 7900 XTXTight · C · Q4_K_Mpainful · offloadbeta
AMD Radeon RX 9070Tight · C · Q4_K_Mpainful · offloadbeta
AMD Radeon RX 9070 XTTight · C · Q4_K_Mpainful · offloadbeta
ASUS Ascent GX10Fits · B · Q8_0painfulbeta
Beelink GTR9 Pro Ryzen AI Max+ 395 128GBFits · B · Q8_0painfulbeta
NVIDIA DGX SparkFits · B · Q8_0painfulbeta
Framework Desktop Ryzen AI Max+ 395 128GBFits · B · Q8_0painfulbeta
Framework Desktop Ryzen AI Max+ 395 64GBWon't fitbeta
GMKtec EVO-X2 Ryzen AI Max+ 395 128GBFits · B · Q8_0painfulbeta
HP Z2 Mini G1a Ryzen AI Max+ PRO 395 128GBFits · B · Q8_0painfulbeta
Mac mini M4 16GBWon't fit
Mac mini M4 24GBWon't fit
Mac mini M4 Pro 24GBWon't fit
Mac mini M4 Pro 48GBWon't fit
Mac Studio M3 Ultra 96GBFits · B · Q5_K_Mpainful
Mac Studio M4 Max 36GBWon't fit
Mac Studio M4 Max 64GBWon't fit

Verdicts computed from published specs and measured GGUF sizes — how the math works.