Radeon RX 7900 XTX

AMD Radeon RX 7900 XTX: 24 GB of memory at 960 GB/s. Below: the open models it can run, estimated at 24 GB with an 8K context. 24 GB of VRAM at 960 GB/s for $999 at launch, $600 less than the RTX 4090: the AMD route to 32B models at 4-bit, using ROCm or Vulkan instead of CUDA.

Last updated: 2026-10-14

Specifications

Memory	24 GB GDDR6[src]
Memory bandwidth	960 GB/s[src]
Power	355 W[src]
Launch	2022-12[src]
Launch price	US$999[src]
Architecture	RDNA 3[src]
Software	ROCm / Vulkan

What it can run

Best-quality quantization that fits with a 8K context, and the estimated generation speed. Estimates, not benchmarks. See the methodology.

Model	Params	Best quant	Memory	tok/s (est.)
Qwen3.5-35B-A3B	35B (3B)	Q4_K_M	21.4 GiB	369
Qwen3.6-35B-A3B	35B (3B)	Q4_K_M	21.4 GiB	369
Qwen3-32B	32.8B	Q4_K_M	21.9 GiB	34
DeepSeek-R1-Distill-Qwen-32B	32.76B	Q4_K_M	21.9 GiB	34
Gemma 4 31B IT	30.7B	Q5_K_M	22.9 GiB	31
Qwen3-30B-A3B (2507)	30.5B (3.3B)	Q5_K_M	22.5 GiB	286
Qwen3-Coder-30B-A3B-Instruct	30.5B (3.3B)	Q5_K_M	22.5 GiB	286
GLM-4.7-Flash (30B-A3B)	30B (3B)	Q5_K_M	21.8 GiB	315
Qwen3.5-27B	27B	Q6_K	22.7 GiB	30
Qwen3.6-27B	27B	Q6_K	22.7 GiB	30
Qwen3.8-27B	27B	Q6_K	22.7 GiB	30
Gemma 3 27B IT	27B	Q6_K	23.3 GiB	30
Gemma 4 26B A4B IT	25.2B (3.8B)	Q6_K	21.1 GiB	215
Mistral Small 3.2 24B Instruct (2506)	24B	Q6_K	21.1 GiB	34
Magistral Small 1.2 (2509)	24B	Q6_K	21.1 GiB	34
Devstral Small 2 24B Instruct (2512)	24B	Q6_K	21.1 GiB	34
gpt-oss-20b	21B (3.6B)	Q8_0	22.5 GiB	176
Phi-4 (14B)	14B	Q8_0	16.6 GiB	45
Gemma 3 12B IT	12B	Q8_0	13.8 GiB	53
Gemma 4 12B Unified IT	11.95B	Q8_0	13.3 GiB	53
Qwen3.5-9B	9B	FP16	18.4 GiB	37
Qwen3-8B	8.2B	FP16	17.7 GiB	41
DeepSeek-R1-0528-Qwen3-8B	8.19B	FP16	17.6 GiB	41
Llama 3.1 8B Instruct	8B	FP16	17.1 GiB	42
Gemma 4 E4B IT	8B	FP16	16.4 GiB	42
Llama 3.2 3B Instruct	3.21B	FP16	7.7 GiB	105
Kimi K2.6	1000B (32B)	Doesn't fit	–	–
DeepSeek-R1-0528 (671B)	671B (37B)	Doesn't fit	–	–
DeepSeek-V4-Flash	284B (13B)	Doesn't fit	–	–
Qwen3.8-Flash-Next	180B (6B)	Doesn't fit	–	–
Qwen3.5-122B-A10B	122B (10B)	Doesn't fit	–	–
Mistral Small 4 119B (2603)	119B (6.5B)	Doesn't fit	–	–
gpt-oss-120b	117B (5.1B)	Doesn't fit	–	–
Llama 4 Scout 17B-16E Instruct	109B (17B)	Doesn't fit	–	–
GLM-4.5-Air	106B (12B)	Doesn't fit	–	–
Qwen3-Coder-Next (80B-A3B)	80B (3B)	Doesn't fit	–	–
Llama 3.3 70B Instruct	70B	Doesn't fit	–	–

Prices

Latest price at each shop, as listed on the day we checked.

Region	Shop	Listing	Price	Per GB	Checked
US	Neweggroboshine	PowerColor Hellhound Radeon RX 7900 XTX 24GB GDDR6 PCI Express 4.0 ATX Graphics Card RX7900XTX 24G-L/OCNewegg marketplace seller; ships from Hong Kong	US$1,353.11	US$56/GB	2026-10-14

US value: about 138.6 tok/s on Llama 3.1 8B Instruct (Q4_K_M, 8K), or 10.2 tok/s per US$100.

A price history chart appears once we have checked this device on two or more days.

All prices →

Frequently asked questions

Which LLMs can the Radeon RX 7900 XTX run?

With 24 GB and an 8K context, the largest models that fit include: Qwen3.5-35B-A3B, Qwen3.6-35B-A3B, Qwen3-32B, DeepSeek-R1-Distill-Qwen-32B, Gemma 4 31B IT. See the full table below.

How fast is the Radeon RX 7900 XTX for local LLMs?

Generation speed is mostly set by memory bandwidth (960 GB/s). For Llama 3.1 8B Instruct at FP16, expect roughly 42 tokens/s; bigger models are slower.

Can the Radeon RX 7900 XTX run 70B models?

Llama 3.3 70B Instruct does not fit on the Radeon RX 7900 XTX (24 GB), even at Q4_K_M with an 8K context.