readygpu

AMD Radeon RX 7800 XT

16 GB · 624 GB/s · 263 W

Prices

Every retailer we track in the US, cheapest first. Buy links may earn us a commission.

RetailerConditionPriceStockCheckedBuy
AmazonPowerColor Fighter AMD Radeon RX 7800 XT 16GB GDDR6 Graphics CardNew$599In stock26 min agoBuy
AmazonPowerColor Hellhound AMD Radeon RX 7800 XT 16GB GDDR6 Graphics Cardrefurbished$630In stock26 min agoBuy
AmazonPowerColor Fighter AMD Radeon RX 7800 XT 16GB GDDR6 Graphics Cardrefurbished$630In stock26 min agoBuy
AmazonSapphire 11330-03-20G Pure AMD Radeon RX 7800 XT Gaming Graphics Card with…refurbished$640In stock26 min agoBuy
AmazonPowerColor Twin Fan AMD Radeon RX 7800 XT 16GB GDDR6New$699In stock26 min agoBuy
AmazonSapphire 11330-01-20G Nitro+ AMD Radeon RX 7800 XT Gaming Graphics Card with…New$757In stock26 min agoBuy
AmazonSapphire Pulse AMD Radeon RX 7800 XT Gaming 16GB GDDR6 Dual Video CardNew$757In stock26 min agoBuy
AmazonXFX Quicksilver AMD Radeon RX 7800 XT Magnetic Air Gaming Graphics Card with…New$798In stock26 min agoBuy
AmazonXFX Speedster SWFT210 Radeon RX 7800XT Gaming Graphics Card with 16GB GDDR6…New$849In stock26 min agoBuy
AmazonSapphire 11330-02-20G Pulse AMD Radeon RX 7800 XT Gaming Graphics Card with…New$895In stock26 min agoBuy
AmazonGIGABYTE Radeon RX 7800 XT Gaming OC 16GB Graphics CardNew$978In stock26 min agoBuy
AmazonGigabyte Radeon RX 7800 XT Gaming OC 16G Graphics CardNew$990+ $10 deliveryIn stock26 min agoBuy
AmazonSAPPHIRE Pulse Radeon RX 7800 XT Gaming 16GB GDDR6 2 Fan Space Saving Graphics…New$1,075In stock26 min agoBuy

Price history

Lowest price shown each day over the last 90 days.

Not enough price history yet.

What two of them run

Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.

ModelQuantFitsMemoryMax contextDecode @128kPrefillGood for
Qwen 3.8 27B

Alibaba Qwen

UD-Q5_K_Mfits28.6 GB154k256k with q8 cache

12tok/sest.

318 tok/schat
Qwen 3.6 27B

Alibaba Qwen

Q5_K_Mfits28.4 GB157k256k with q8 cache

12tok/sest.

318 tok/schat
Gemma 4 31B

Google

Q4_K_Mfits29.9 GB133k245k with q8 cache

12tok/sest.

302 tok/schat
Qwen 3.6 35B-A3B

Alibaba Qwen

UD-Q5_K_Mfits29.2 GB173k256k with q8 cache

42tok/sest.

1547 tok/schat, coding, agents, long documents
Qwen 3.5 27B

Alibaba Qwen

Q5_K_Mfits28.5 GB156k256k with q8 cache

12tok/sest.

318 tok/schat
Gemma 4 26B-A4B

Google

Q8_0fits29.8 GB153k245k with q8 cache

29tok/sest.

1878 tok/schat, coding, agents, long documents
Qwen 3.5 35B-A3B

Alibaba Qwen

Q5_K_Mfits29.1 GB180k256k with q8 cache

42tok/sest.

1547 tok/schat, coding, agents, long documents
GLM 4.7 Flash

Z.ai

Q5_K_Mfits28.6 GB159k198k with q8 cache

19tok/sest.

730 tok/schat, coding, agents, long documents
gpt-oss 20B

OpenAI

MXFP4fits16.3 GB128k

36tok/sest.

1216 tok/schat, coding, agents, long documents
Gemma 4 12B

Google

Q8_0fits16.2 GB256k

23tok/sest.

781 tok/schat, coding, long documents
Qwen 3.5 9B

Alibaba Qwen

Q8_0fits15.0 GB256k

25tok/sest.

928 tok/schat, coding, long documents
Gemma 3 27B

Google

Q4_K_Mfits27.9 GB128k

12tok/sest.

390 tok/schat
Ministral 3 14B

Mistral AI

Q4_K_Mfits29.7 GB132k241k with q8 cache

12tok/sest.

366 tok/schat, coding
DeepSeek R1 0528 Qwen3 8B

DeepSeek

Q8_0fits28.2 GB128k

12tok/sest.

471 tok/schat, coding
Qwen3 8B

Alibaba Qwen

Q8_0fits28.2 GB40k

12tok/sest.

471 tok/schat, coding
Qwen 3.5 4B

Alibaba Qwen

Q8_0fits10.3 GB256k

39tok/sest.

1446 tok/schat, coding, long documents
Ministral 3 8B

Mistral AI

Q8_0fits27.5 GB149k256k with q8 cache

13tok/sest.

477 tok/schat, coding
Granite 4.2 8B

IBM

Q6_Kfits29.1 GB128k

12tok/sest.

428 tok/schat, coding
Gemma 4 E4B

Google

Q8_0fits13.2 GB128k

29tok/sest.

1302 tok/schat, coding, long documents
LFM2.5 8B-A1B

Liquid AI

Q8_0fits16.4 GB125k

27tok/sest.

1740 tok/schat, coding, long documents
Llama 3.1 8B

Meta

Q6_Kfits24.2 GB128k

14tok/sest.

514 tok/schat, coding
Qwen 3.5 122B-A10B

Alibaba Qwen

UD-Q2_K_XLoffload44.2 GB–

11tok/sest.

455 tok/schat
Qwen3 Coder Next

Alibaba Qwen

Q4_K_Moffload50.3 GB–

11tok/sest.

944 tok/schat, coding
Nemotron 3 Super 120B-A12B

NVIDIA

UD-Q2_K_XLoffload54.1 GB–

9tok/sest.

578 tok/s–
Mistral Small 4 119B

Mistral AI

UD-Q2_K_XLoffload42.3 GB–

15tok/sest.

404 tok/schat, coding
Qwen3 Next 80B-A3B

Alibaba Qwen

Q4_K_Moffload50.3 GB–

13tok/sest.

1032 tok/schat, coding
Devstral Small 2 24B

Mistral AI

Q4_K_Moffload35.4 GB97k177k with q8 cache

5tok/sest.

259 tok/schat
Nemotron 3.5 Lightning 30B-A3B

NVIDIA

UD-Q6_K_XLoffload35.4 GB–

27tok/sest.

1893 tok/schat, coding, agents, long documents
Kimi Linear 48B-A3B

Moonshot AI

Q4_K_Moffload31.1 GB78k107k with q8 cache

62tok/sest.

1145 tok/schat, coding, long documents
Qwen3 Coder 30B-A3B

Alibaba Qwen

Q4_K_Moffload31.3 GB118k212k with q8 cache

12tok/sest.

442 tok/schat, coding, agents
Qwen3 32B

Alibaba Qwen

Q4_K_Moffload52.5 GB40k

2tok/sest.

94 tok/schat
Mistral Small 3.2 24B

Mistral AI

Q4_K_Moffload35.4 GB97k128k with q8 cache

5tok/sest.

259 tok/schat
DeepSeek R1 Distill Qwen 32B

DeepSeek

Q4_K_Moffload52.5 GB41k76k with q8 cache

2tok/sest.

126 tok/schat
Qwen3 14B

Alibaba Qwen

Q4_K_Moffload30.4 GB40k

11tok/sest.

311 tok/schat, coding
Phi-4 14B

Microsoft

Q4_K_Moffload35.3 GB16k

5tok/sest.

284 tok/schat, coding
DeepSeek V4 Flash

DeepSeek

UD-Q2_K_XLwon't run103.0 GB––––
GLM 5.3 Flash

Z.ai

UD-Q2_K_XLwon't run104.8 GB––––
Qwen 3.8 Flash Next

Alibaba Qwen

UD-Q2_K_XLwon't run78.6 GB––––
MiniMax M2.7

MiniMax

UD-Q2_K_XLwon't run103.2 GB––––
gpt-oss 120B

OpenAI

MXFP4won't run65.6 GB––––
GLM 4.5 Air

Z.ai

Q2_Kwon't run67.3 GB––––
Llama 3.3 70B

Meta

Q4_K_Mwon't run81.7 GB––––

Specifications

From the manufacturer's published specifications; sources are linked where we have them.

GPU
Radeon RX 7800 XT
Memory
16 GB GDDR6
Memory bus
256-bit
Memory bandwidth
624 GB/s
FP16 compute
74 TFLOPS
Software
ROCm
Board power
263 W
PCIe generation
Gen 4
PCIe lanes
x16

Compare with