AMD Radeon RX 7900 XT: 20 GB, what it runs and what it costs

Name: AMD Radeon RX 7900 XT
Brand: AMD

Specs checked Sep 20, 2026 · Aliteq Team · How we compute this

The short answer

The AMD Radeon RX 7900 XT has 20 GB of VRAM and 800 GB/s of memory bandwidth (2022). At Q4_K_M quality or better with an 8K context it runs 24 of the open models we track; the largest that fits with room to spare is Mistral Small 24B. We don't see it for rent on the providers we track right now.

VRAM: 20 GB
Bandwidth: 800 GB/s
Board power: 315 W
Launched: 2022

Source: AMD specification · bandwidth not yet confirmed by a second source, so we don't estimate speed from it

Buy it or rent it

Not for rent on the providers we track right now. See every card that is.

Which AI models run on the AMD Radeon RX 7900 XT

Computed by our VRAM engine for an 8K context: the best quality each model fits at in 20 GB. Speeds are upper-bound estimates from memory bandwidth, not benchmarks.

Model	Best fit	VRAM used	~tok/s
NVIDIA Nemotron 3 Nano 30B-A3B (MoE)	Q4_K_M	19 GB93% · tight	—
Gemma 4 31B	Q4_K_M	19 GB95% · tight	—
Qwen3 30B-A3B (MoE)	Q4_K_M	19 GB94% · tight	—
Qwen3-Coder 30B-A3B (MoE)	Q4_K_M	19 GB94% · tight	—
Qwen3.5 27B	Q5_K_M	20 GB98% · tight	—
Qwen3.6 27B	Q5_K_M	20 GB98% · tight	—
Qwen3.8 27B	Q5_K_M	20 GB98% · tight	—
Gemma 4 26B-A4B (MoE)	Q5_K_M	18 GB90% · tight	—
Mistral Small 24B	Q5_K_M	18 GB88%	—
gpt-oss 20B (MoE)	Q6_K	17 GB86%	—
DeepSeek R1 Distill 14B	Q8_0	17 GB84%	—
Qwen2.5-Coder 14B	Q8_0	17 GB84%	—

Fits only below Q4 quality: Mixtral 8x7B (MoE) (Q2_K), Qwen3.6 35B-A3B (MoE) (Q4_0), Ornith-1.5 35B-A3B (MoE) (Q4_0), Qwen3.5 35B-A3B (MoE) (Q4_0), DeepSeek R1 Distill 32B (IQ4_XS).

Too big for 20 GB (rent a bigger card instead): what it costs to run DeepSeek R1 Distill 70B, what it costs to run Qwen3-Coder-Next 80B-A3B (MoE), what it costs to run Qwen3-Next 80B-A3B (MoE), what it costs to run GLM-4.5-Air (MoE).

Check a model and context of your own in the VRAM calculator.

Our guides on the AMD Radeon RX 7900 XT

Compareeveryone says AMD means fighting ROCm for local AI. on llama.cpp, the thing you're told to install is the slower one

Cards to compare it with

Every card by VRAM tier: all GPUs for gaming and local AI.

AMD Radeon RX 7900 XT: common questions

How much VRAM does the AMD Radeon RX 7900 XT have?

20 GB, with 800 GB/s of memory bandwidth, per the maker's specification.

What is the biggest AI model the AMD Radeon RX 7900 XT can run?

Of the open models we track, Mistral Small 24B is the largest that fits at Q4_K_M or better with an 8K context and room to spare (about 18 GB of 20 GB). NVIDIA Nemotron 3 Nano 30B-A3B (MoE) also squeezes in, but with almost no memory left for longer context. Bigger models only fit at lower-quality quants or need more memory.

Can I rent an AMD Radeon RX 7900 XT in the cloud?

We don't see it on Vast.ai, Runpod or the other providers we track right now. The cloud GPU table lists every card that is for rent.

Is 20 GB enough?

4K gaming; 24–32B local models at Q4 with room for context.