Which is better for local AI, the AMD Radeon RX 7900 XT or the AMD Radeon RX 9070?

Choose the AMD Radeon RX 7900 XT to run bigger models. Choose the AMD Radeon RX 7900 XT for speed.

AMD Radeon RX 7900 XT vs AMD Radeon RX 9070 for local AI (UK)

In short

The AMD Radeon RX 7900 XT has more memory for models: 20 GB against 16 GB. At 64k context the AMD Radeon RX 7900 XT runs 36 of the models we track fully in memory and the AMD Radeon RX 9070 31; only the AMD Radeon RX 7900 XT holds Gemma 4 26B-A4B. On the models both run fully in memory, the AMD Radeon RX 7900 XT is about 1.2× as fast as the AMD Radeon RX 9070 (estimated, median across models).

Updated 26 October 2026. Speeds are estimates; how they are worked out.

Specifications

Spec	AMD Radeon RX 7900 XT	AMD Radeon RX 9070
GPU	Radeon RX 7900 XT	Radeon RX 9070
Memory	20 GB GDDR6	16 GB GDDR6
Memory bus	320-bit	256-bit
Memory bandwidth	800 GB/s	640 GB/s
FP16 compute	103 TFLOPS	36.1 TFLOPS
Software	ROCm	ROCm
Board power	315 W	220 W
PCIe generation	Gen 4	Gen 5
PCIe lanes	x16	x16

What each runs

Estimated decode speed with the most precise quant that fits each one est.

Model	AMD Radeon RX 7900 XT	AMD Radeon RX 9070
Gemma 4 26B-A4B	63tok/sQ4_K_M	offload
gpt-oss 20B	65tok/sMXFP4	52tok/sMXFP4
Gemma 4 12B	31tok/sQ8_0	25tok/sQ8_0
Qwen 3.5 9B	38tok/sQ8_0	30tok/sQ8_0
Ministral 3 14B	23tok/sQ4_K_M	offload
DeepSeek R1 0528 Qwen3 8B	24tok/sQ8_0	24tok/sQ4_K_M
Qwen3 8B	24tok/sQ8_0	24tok/sQ4_K_M
Qwen 3.5 4B	66tok/sQ8_0	53tok/sQ8_0
Ministral 3 8B	24tok/sQ8_0	25tok/sQ4_K_M
Granite 4.2 8B	24tok/sQ6_K	offload
Gemma 4 E4B	44tok/sQ8_0	35tok/sQ8_0
LFM2.5 8B-A1B	62tok/sQ8_0	49tok/sQ8_0
Llama 3.1 8B	29tok/sQ6_K	25tok/sQ5_K_M
Qwen2.5 0.5B	329tok/sQ8_0	263tok/sQ8_0
Qwen3.5 0.8B	269tok/sQ8_0	215tok/sQ8_0
Qwen3.5 2B	195tok/sQ5_K_M	156tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B	117tok/sQ8_0	93tok/sQ8_0
MiniCPM5 2B	80tok/sQ8_0	64tok/sQ8_0
Spark X2.5 4B	80tok/smlx-4bit	64tok/smlx-4bit
Mellum2.1 12B A2.5B Thinking	73tok/sQ8_0	58tok/sQ8_0
FrogNano 4B 2609	65tok/sQ8_0	52tok/sQ8_0
LFM2.5 2.6B	64tok/sQ8_0	51tok/sQ8_0
LFM2.5 VL 3B	64tok/sQ8_0	51tok/sQ8_0
Kimi VL A3B	58tok/smlx-6bit	50tok/smlx-5bit
Kimi VL A3B Thinking 2506	51tok/sQ8_0	53tok/sQ4_K_M
granite vision 4.1 4b	49tok/sQ8_0	39tok/sQ8_0
granite 4.2 3b	48tok/sQ8_0	38tok/sQ8_0
Ministral 3 3B Instruct 2512	41tok/sQ8_0	33tok/sQ8_0
GLM 4 9B 0414	40tok/smlx-5bit	32tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B	37tok/sQ8_0	30tok/sQ8_0
GLM 4.6V Flash	35tok/sQ8_0	28tok/sQ8_0
GLM 4.1V 9B Thinking	30tok/smlx-8bit	24tok/smlx-8bit
DeepSeek R1 Distill Llama 8B	26tok/sQ8_0	25tok/sQ5_K_M
Ministral 3 8B Reasoning 2512	24tok/sQ8_0	25tok/sQ4_K_M
Muse Glimmer 30B	24tok/sQ4_K_M	offload
Ministral 3 14B Reasoning 2512	23tok/sQ4_K_M	offload
Qwen 3.8 27B	offload	offload
Qwen 3.5 122B-A10B	offload	won't run
Qwen 3.6 27B	offload	offload
Gemma 4 31B	offload	offload
Mistral Small 4 119B	offload	offload
Qwen 3.6 35B-A3B	offload	offload
Qwen 3.5 27B	offload	offload
Qwen 3.5 35B-A3B	offload	offload
GLM 4.7 Flash	offload	offload
Devstral Small 2 24B	offload	offload
Nemotron 3.5 Lightning 30B-A3B	offload	offload
Kimi Linear 48B-A3B	offload	offload
Qwen3 Coder 30B-A3B	offload	offload
Qwen3 32B	offload	offload
Gemma 3 27B	offload	offload
Mistral Small 3.2 24B	offload	offload
DeepSeek R1 Distill Qwen 32B	offload	offload
Qwen3 14B	offload	offload
Phi-4 14B	offload	offload
LFM2.5 24B A2B	offload	offload
DeepSeek R1 Distill Qwen 14B	offload	offload
Devstral Small 2507	offload	offload
Magistral Small 2506	offload	offload
Magistral Small 2507	offload	offload
Magistral Small 2509	offload	offload
Qwen3.8 27B OBLITERATED	offload	offload
granite 4.2 30b	offload	offload
DeepSeek V4 Flash	won't run	won't run
GLM 5.3 Flash	won't run	won't run
Qwen 3.8 Flash Next	won't run	won't run
MiniMax M2.7	won't run	won't run
Nemotron 3 Super 120B-A12B	won't run	won't run
Qwen3 Coder Next	won't run	won't run
gpt-oss 120B	won't run	won't run
GLM 4.5 Air	won't run	won't run
Qwen3 Next 80B-A3B	won't run	won't run
Llama 3.3 70B	won't run	won't run
DeepSeek R1	won't run	won't run
DeepSeek R1 0528	won't run	won't run
DeepSeek R1 Distill Llama 70B	won't run	won't run
DeepSeek R1 Zero	won't run	won't run
DeepSeek V3	won't run	won't run
DeepSeek V3 0324	won't run	won't run
DeepSeek V3.1	won't run	won't run
DeepSeek V3.1 Terminus	won't run	won't run
DeepSeek V3.2	won't run	won't run
DeepSeek V4 Flash 0731	won't run	won't run
DeepSeek V4 Flash Vision Exp	won't run	won't run
Devstral 2 123B Instruct 2512	won't run	won't run
GLM 4.5	won't run	won't run
GLM 4.5V	won't run	won't run
GLM 4.6	won't run	won't run
GLM 4.6V	won't run	won't run
GLM 4.7	won't run	won't run
GLM 5	won't run	won't run
GLM 5.1	won't run	won't run
GLM 5.2	won't run	won't run
GLM 5.3	won't run	won't run
Kimi Dev 72B	won't run	won't run
Kimi K2	won't run	won't run
Kimi K2 Instruct 0905	won't run	won't run
Kimi K2 Thinking	won't run	won't run
Kimi K2.5	won't run	won't run
MiniMax M2	won't run	won't run
MiniMax M2.1	won't run	won't run
MiniMax M2.5	won't run	won't run
MiniMax M3	won't run	won't run
Mistral Medium 3.5 128B	won't run	won't run

Questions

Which is better for local AI, the AMD Radeon RX 7900 XT or the AMD Radeon RX 9070?: Choose the AMD Radeon RX 7900 XT to run bigger models. Choose the AMD Radeon RX 7900 XT for speed.
Which can run bigger models, the AMD Radeon RX 7900 XT or the AMD Radeon RX 9070?: At 64k context the AMD Radeon RX 7900 XT runs 36 of the models we track fully in memory and the AMD Radeon RX 9070 31; only the AMD Radeon RX 7900 XT holds Gemma 4 26B-A4B.
Which is faster for local AI, the AMD Radeon RX 7900 XT or the AMD Radeon RX 9070?: On the models both run fully in memory, the AMD Radeon RX 7900 XT is about 1.2× as fast as the AMD Radeon RX 9070 (estimated, median across models).

AMD Radeon RX 7900 XT vs AMD Radeon RX 9070

In short

Specifications

What each runs

Questions

More comparisons

More hardware for local AI