TokenAssemble

Alibaba/Qwen · open-weights model

Qwen2.5-14B-Instruct

Qwen2.5-14B-Instruct is a 14.8B-parameter model by Alibaba/Qwen. Its smallest quant (Q4_K_M) needs at least 11.1GB of GPU-addressable memory at 8K context; it loads cleanly at a quality quant on 36 of the 50 machines we track.

Parameters
14.8B
Layers
48
Max context
32K
Attention
GQA
License
apache-2.0

Config from Qwen/Qwen2.5-14B-Instruct

Quants and what they need

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

QuantFile sizeNeeds ≥
Q8_015.7 GB17.8 GB
Q6_K12.1 GB14.2 GB
Q5_K_M10.5 GB12.6 GB
Q4_K_M9.0 GB11.1 GB

What runs Qwen2.5-14B-Instruct

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

HardwareBest-quant verdict · llama.cpp · 8K context
Intel Arc A770 16 GBFits · B · Q5_K_Minteractivebeta
Intel Arc B580Tight · C · Q4_K_Minteractivebeta
AMD Radeon PRO W7900Fits · A+ · Q8_0interactivebeta
NVIDIA GeForce RTX 3060 12 GBTight · C · Q4_K_Minteractive
NVIDIA GeForce RTX 3070Tight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 3070 TiTight · C · Q4_K_Minteractive · offloadbeta
NVIDIA GeForce RTX 3080 10 GBTight · C · Q4_K_Minteractive · offloadbeta
NVIDIA GeForce RTX 3080 12 GBTight · C · Q4_K_Minteractive
NVIDIA GeForce RTX 3080 TiTight · C · Q4_K_Minteractive
NVIDIA GeForce RTX 3090Fits · B · Q8_0interactive
NVIDIA GeForce RTX 3090 TiFits · B · Q8_0interactive
NVIDIA GeForce RTX 4060Tight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 4060 Ti 16 GBFits · B · Q5_K_Musable
NVIDIA GeForce RTX 4060 Ti 8 GBTight · C · Q4_K_Musable · offloadbeta
NVIDIA GeForce RTX 4070Tight · C · Q4_K_Minteractive
NVIDIA GeForce RTX 4070 SUPERTight · C · Q4_K_Minteractive
NVIDIA GeForce RTX 4070 TiTight · C · Q4_K_Minteractive
NVIDIA GeForce RTX 4070 Ti SUPERFits · B · Q5_K_Minteractive
NVIDIA GeForce RTX 4080Fits · B · Q5_K_Minteractive
NVIDIA GeForce RTX 4080 SUPERFits · B · Q5_K_Minteractive
NVIDIA GeForce RTX 4090Fits · B · Q8_0interactive
NVIDIA RTX 5000 Ada GenerationFits · A+ · Q8_0interactive
NVIDIA GeForce RTX 5060 Ti 16 GBFits · B · Q5_K_Minteractive
NVIDIA GeForce RTX 5070Tight · C · Q4_K_Minteractive
NVIDIA GeForce RTX 5070 TiFits · B · Q5_K_Minteractive
NVIDIA GeForce RTX 5080Fits · B · Q5_K_Minteractive
NVIDIA GeForce RTX 5090Fits · A+ · Q8_0interactive
NVIDIA RTX 6000 Ada GenerationFits · A+ · Q8_0interactive
NVIDIA RTX A6000Fits · A+ · Q8_0interactive
AMD Radeon RX 6800Fits · B · Q5_K_Minteractivebeta
AMD Radeon RX 6900 XTFits · B · Q5_K_Minteractivebeta
AMD Radeon RX 7800 XTFits · B · Q5_K_Minteractivebeta
AMD Radeon RX 7900 XTFits · B · Q6_Kinteractivebeta
AMD Radeon RX 7900 XTXFits · B · Q8_0interactivebeta
AMD Radeon RX 9070Fits · B · Q5_K_Minteractivebeta
AMD Radeon RX 9070 XTFits · B · Q5_K_Minteractivebeta
ASUS Ascent GX10Fits · A+ · Q8_0usablebeta
Beelink GTR9 Pro Ryzen AI Max+ 395 128GBFits · A+ · Q8_0usablebeta
NVIDIA DGX SparkFits · A+ · Q8_0usablebeta
Framework Desktop Ryzen AI Max+ 395 128GBFits · A+ · Q8_0usablebeta
Framework Desktop Ryzen AI Max+ 395 64GBFits · A+ · Q8_0usablebeta
GMKtec EVO-X2 Ryzen AI Max+ 395 128GBFits · A+ · Q8_0usablebeta
HP Z2 Mini G1a Ryzen AI Max+ PRO 395 128GBFits · A+ · Q8_0usablebeta
Mac mini M4 16GBTight · C · Q4_K_Mpainful
Mac mini M4 24GBFits · B · Q6_Kpainful
Mac mini M4 Pro 24GBFits · B · Q6_Kusable
Mac mini M4 Pro 48GBFits · A+ · Q8_0usable
Mac Studio M3 Ultra 96GBFits · A+ · Q8_0interactive
Mac Studio M4 Max 36GBFits · A+ · Q8_0usable
Mac Studio M4 Max 64GBFits · A+ · Q8_0usable

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