Tesla P4 8GB vs RX 7900 XTX 24GB for Local LLMs

The RX 7900 XTX 24GB has about 400% more memory bandwidth (960 vs 192 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 400% faster on the RX 7900 XTX 24GB. The RX 7900 XTX 24GB fits more of the catalog at Q4/8K — 35 vs 16 of 69 models (24 vs 8 GB VRAM). Largest model that fits the RX 7900 XTX 24GB but not the Tesla P4 8GB: Qwen3.6-35B-A3B (36.0B). MSRP is $80 for the Tesla P4 8GB vs $999 for the RX 7900 XTX 24GB. MSRP is a launch list price, not live retail — Amazon prices move; click through for the current price. In the Q4/8K head-to-head below (39 shared models), the RX 7900 XTX 24GB posts the higher tok/s in 39 rows vs 0. Methodology.

Spec comparison

	Tesla P4 8GB	RX 7900 XTX 24GB
Vendor	NVIDIA	AMD
VRAM	8 GB	24 GB
Memory type	GDDR5	GDDR6
Memory bandwidth	192 GB/s	960 GB/s
TDP	75 W	355 W
MSRP (list)	$80	$999
Buy	Search Amazon (affiliate)	ASRock Radeon RX 7900 XTX Phantom Gaming 24GB OC (affiliate) · More listings

MSRP is the launch list price, not live retail. Buy links are Amazon affiliate links — the price after you click is the live price.

Q4 / 8K head-to-head — top 15 of 39 shared models

Model	Params (B)	Tesla P4 8GB tok/s	Tesla P4 8GB fits	RX 7900 XTX 24GB tok/s	RX 7900 XTX 24GB fits	Winner
MiniCPM5-1B	1.08	113.1 est.	Yes	565.7 est.	Yes	RX 7900 XTX 24GB
Qwen3.5-2B	2.0	61.1 est.	Yes	305.5 est.	Yes	RX 7900 XTX 24GB
DeepSeek-R1-0528-Qwen3-8B-layer-mix-bpw-3.8-mlx	2.3	53.1 est.	Yes	265.6 est.	Yes	RX 7900 XTX 24GB
Qwen3.6-35B-A3B	36.0	17.0 est.	No	203.6 est.	Yes	RX 7900 XTX 24GB
Qwen3.5-35B-A3B	34.7	18.2 est.	No	203.6 est.	Yes	RX 7900 XTX 24GB
GLM-4.7-Flash	31.2	21.0 est.	No	203.6 est.	Yes	RX 7900 XTX 24GB
Qwen3-30B-A3B-Instruct-2507	30.5	21.9 est.	No	203.6 est.	Yes	RX 7900 XTX 24GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16	30.0	24.1 est.	No	203.6 est.	Yes	RX 7900 XTX 24GB
Ornith-1.0-35B	35.0	17.0 est.	No	203.6 est.	Yes	RX 7900 XTX 24GB
qwen35b-a3b-fable-sft-abliterated	34.7	17.3 est.	No	203.6 est.	Yes	RX 7900 XTX 24GB
Llama-3.2-3B-Instruct	3.2	38.2 est.	Yes	190.9 est.	Yes	RX 7900 XTX 24GB
gpt-oss-20b	21.5	33.6 est.	No	169.7 est.	Yes	RX 7900 XTX 24GB
gemma-4-26B-A4B-it	25.2	23.9 est.	No	160.8 est.	Yes	RX 7900 XTX 24GB
Qwen3-4B-Instruct-2507	4.0	30.5 est.	Yes	152.7 est.	Yes	RX 7900 XTX 24GB
NVIDIA-Nemotron-3-Nano-4B-BF16	4.0	30.5 est.	Yes	152.7 est.	Yes	RX 7900 XTX 24GB

est. = bandwidth-based estimate; measured = curated real benchmark that overrides the estimate. Fits = weights + KV(8K) + 1 GB overhead ≤ 95% of VRAM.

Fit coverage at Q4 / 8K

	Tesla P4 8GB	RX 7900 XTX 24GB
Catalog models that fit	16 of 69	35 of 69
Largest exclusive fit	—	Qwen3.6-35B-A3B (36.0B)

Tesla P4 8GB details → · RX 7900 XTX 24GB details →