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

The AMD Radeon RX 7900 XT has 20 GB of GDDR6 with 800 GB/s memory bandwidth.

What is the AMD Radeon RX 7900 XT best for?

With 20 GB of VRAM, the AMD Radeon RX 7900 XT handles smaller models (7B–14B) at Q4–Q5 quantization, ideal for entry-level local LLM experimentation and lightweight inference.

What LLMs can the AMD Radeon RX 7900 XT run locally?

The AMD Radeon RX 7900 XT can run 51 of the 97 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Qwen 3.8 27B at Q3_K_M, Ornith 1.5 35B-A3B (MoE) at Q2_K, Ornith 1.5 9B at Q8_0.

Can the AMD Radeon RX 7900 XT run Gemma 4 31B?

Yes. The AMD Radeon RX 7900 XT runs Gemma 4 31B natively in VRAM at Q3_K_M quantization, achieving approximately 31.9 tokens per second.

Can the AMD Radeon RX 7900 XT run Qwen 3.6 27B?

Yes. The AMD Radeon RX 7900 XT runs Qwen 3.6 27B natively in VRAM at Q3_K_M quantization, achieving approximately 38.5 tokens per second.

Can the AMD Radeon RX 7900 XT run Qwen3 8B?

Yes. The AMD Radeon RX 7900 XT runs Qwen3 8B natively in VRAM at Q8_0 quantization, achieving approximately 53.5 tokens per second.

AMD Radeon RX 7900 XT

The AMD Radeon RX 7900 XT has 20 GB VRAM and 800 GB/s memory bandwidth. It can run 51 of our 97 tracked models natively in VRAM at 8k context.

With 20 GB GDDR6, the AMD Radeon RX 7900 XT is a consumer-tier GPU that can run 51 models natively. 7B-14B at Q4 native. 27B tight at Q4. ~7-12 t/s for 7B.

The AMD Radeon RX 7900 XT features 20GB GDDR6 at 800 GB/s on the RDNA 3 architecture. The unique 20GB capacity puts it between 16GB and 24GB tiers, comfortably holding 14B models at Q5 and some 27B models at aggressive Q3–Q4 quantization. A compelling mid-range option for AMD users on Linux with ROCm support.

AMD Radeon RX 7900 XT: 20GB GDDR6 at 800 GB/s, RDNA 3 mid-range.

7B-14B at Q4 native. 27B tight at Q4. ~7-12 t/s for 7B.

ROCm Linux support. Vulkan on Windows. 20GB is awkward capacity.

Vendor	AMD
Architecture	RDNA 3
VRAM	20 GB
Memory type	GDDR6
Memory bandwidth	800 GB/s
Compute backend	ROCM
Tier	Consumer
Released	2022
Models (native)	51 / 97
Models (offload)	6 / 97

Software: ROCm is Linux-only; on Windows use the Vulkan backend instead. Requires llama.cpp compiled with ROCm support.

Popular models for this GPU

Qwen 3.5 35B-A3B (MoE)Qwen 3.6 35B Ornith 1.5 35B-A3B (MoE)Yi 1.5 34B Chat Qwen3 32B

Models this GPU runs natively in VRAM (51)

Show 46 more

Models that fit with CPU offload (6)

These use system RAM for layers that don't fit in VRAM, so expect much slower inference.

Too large for this GPU (40)

Continue reading

vram-guides9 min

Best LLMs for 16 GB VRAM GPUs (2026)

hardware9 min

Best GPUs $500-$1000 for LLMs (2026)

hardware10 min

AMD Radeon for LLMs: ROCm & Vulkan Complete Guide

Frequently asked questions

How much VRAM does the AMD Radeon RX 7900 XT have?: The AMD Radeon RX 7900 XT has 20 GB of GDDR6 with 800 GB/s memory bandwidth.
What is the AMD Radeon RX 7900 XT best for?: With 20 GB of VRAM, the AMD Radeon RX 7900 XT handles smaller models (7B–14B) at Q4–Q5 quantization, ideal for entry-level local LLM experimentation and lightweight inference.
What LLMs can the AMD Radeon RX 7900 XT run locally?: The AMD Radeon RX 7900 XT can run 51 of the 97 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Qwen 3.8 27B at Q3_K_M, Ornith 1.5 35B-A3B (MoE) at Q2_K, Ornith 1.5 9B at Q8_0.
Can the AMD Radeon RX 7900 XT run Gemma 4 31B?: Yes. The AMD Radeon RX 7900 XT runs Gemma 4 31B natively in VRAM at Q3_K_M quantization, achieving approximately 31.9 tokens per second.
Can the AMD Radeon RX 7900 XT run Qwen 3.6 27B?: Yes. The AMD Radeon RX 7900 XT runs Qwen 3.6 27B natively in VRAM at Q3_K_M quantization, achieving approximately 38.5 tokens per second.
Can the AMD Radeon RX 7900 XT run Qwen3 8B?: Yes. The AMD Radeon RX 7900 XT runs Qwen3 8B natively in VRAM at Q8_0 quantization, achieving approximately 53.5 tokens per second.