AMD / discrete

AMD Radeon™ RX 7900 XTX

24 GB decides what fits. 960 GB/s decides how fast it runs once it does.

Open in the calculator →Best models for 24 GB, on every card that size →

Find one: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.

Quick answer

The AMD Radeon™ RX 7900 XTX fits 214 of 320 sized models entirely in its 24 GB; the largest widely used one is Qwen3.6-35B-A3B (23.1 GB at Q4_K_M). Memory decides what fits; its 960 GB/s of bandwidth decides how fast it answers.

Largest popular model that fitsQwen3.6-35B-A3B36B params · Q4_K_M · needs 23.1 GB~403 tok/s Faster than you readOpen in the calculator →
Most downloaded that fitsQwen3.8-27B28B params · Q4_K_M · needs 18.6 GB~51 tok/s Faster than you readOpen in the calculator →

At 8,192 tokens of context with the whole model in device memory. Speeds are estimates from memory bandwidth, not benchmarks run on this card.

AMD Radeon™ RX 7900 XTX · 24 GB · 960 GB/s · Q4_K_M where published · 8,192 tokensSpecificationpublished dataDecode speedestimate

214 of 320 fit entirely

214 of the 320 models the engine can size fit entirely in device memory at Q4_K_M where it is published, otherwise the nearest published format, and 8,192 tokens. 19 run with some layers on system memory (32 GB assumed), and 87 do not run at all.

67%of the models the engine can size fit entirely

24GB of device memory

960GB/s memory bandwidth

19run with system memory

87do not run at 8,192 tokens

Featured models · Q4_K_M at 8,192 tokens, including offload

Model	Needs	Verdict	Decode	Calculator
Qwen3.5-2B2.3B parameters	2.32 GB	fits	~606 tok/s	Open →
NVIDIA-Nemotron-3-Nano-4B-BF164.0B parameters	3.46 GB	fits	~281 tok/s	Open →
Qwen3-VL-8B-Instruct8.8B parameters	7.04 GB	fits	~127 tok/s	Open →
Qwen3.5-9B9.7B parameters	7.05 GB	fits	~154 tok/s	Open →
gemma-4-12B-it12B parameters	9.54 GB	fits	~92 tok/s	Open →
gpt-oss-20b21B parameters	13.8 GB	fits	~299 tok/s	Open →
Qwen3.8-27B28B parameters	18.6 GB	fits	~51 tok/s	Open →
Qwen3.6-27B28B parameters	18.6 GB	fits	~51 tok/s	Open →
Kimi-Linear-48B-A3B-Instruct49B parameters	30.4 GB	6 of 27 layers on system RAM (6.55 GB)	~118 tok/s with offload	Open →
Qwen3.8-Flash-Next180B parameters	111.6 GB	needs 89.8 GB of system RAM; 32 GB assumed	does not run	Open →
DeepSeek-V4-Flash-Vision-Exp305B parameters	188.1 GB	needs 165.5 GB of system RAM; 32 GB assumed	does not run	Open →
GLM-5.3-Flash321B parameters	198.3 GB	needs 175.3 GB of system RAM; 32 GB assumed	does not run	Open →

These examples are selected from prominent labs using the catalogue’s latest Hugging Face 30-day downloads and repository-creation freshness signal, with newer releases guaranteed a place. Offloaded rows assume 32 GB of system RAM, and a speed is only shown for a row that runs. Fitting in memory is not the same as loading: whether the runtime and version you have supports each architecture and format on this machine has not been tested here. Each “Open” link carries the same model, format, context and RAM into the calculator.

Fits entirely in AMD Radeon™ RX 7900 XTX memory — 214 of 320 sized models

Every model that fitswhole model resident · offload off

The most demanding model that fits is Qwen2.5-VL-32B-Instruct at Q4_K_M: 23.5 GB of the 24 GB, leaving 0.52 GB spare.

Fully resident at 8,192 tokens (or the model’s own maximum, where that is shorter), offload off, at 960 GB/s. Each row is a run of the engine for this configuration; the rows start with current, prominent releases and “fits” is memory, not a tested runtime. Older or less prominent models remain available through this search and “Show all”.

Find a model in this list

Showing 40 of 214 models that fit.

Model	Format	Needs	Spare	Decode	Downloads / 30d	Calculator
Qwen3.8-27BQwen · 28B params	Q4_K_M	18.6 GB	5.45 GB	~51 tok/s	6.9M	Open →
gemma-4-26B-A4B-itGoogle · 26B params	Q4_K_M	16.8 GB	7.21 GB	~281 tok/s	13M	Open →
gemma-4-31B-itGoogle · 31B params	Q4_K_M	22.2 GB	1.83 GB	~36 tok/s	9.9M	Open →
Qwen3.5-9BQwen · 9.7B params	Q4_K_M	7.05 GB	17.0 GB	~154 tok/s	9M	Open →
Qwen3.5-4BQwen · 4.7B params	Q4_K_M	3.98 GB	20.0 GB	~277 tok/s	7.8M	Open →
Qwen3.6-35B-A3BQwen · 36B params	Q4_K_M	23.1 GB	0.90 GB	~403 tok/s	3.3M	Open →
gemma-4-12B-itGoogle · 12B params	Q4_K_M	9.54 GB	14.5 GB	~92 tok/s	1.9M	Open →
Qwen3.6-27BQwen · 28B params	Q4_K_M	18.6 GB	5.45 GB	~51 tok/s	2.5M	Open →
Qwen3.5-2BQwen · 2.3B params	Q4_K_M	2.32 GB	21.7 GB	~606 tok/s	4.9M	Open →
gemma-4-E4B-itGoogle · 8.0B params	Q4_K_M	5.86 GB	18.1 GB	~247 tok/s	4.4M	Open →
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA · 32B params	Q4_K_M	20.3 GB	3.71 GB	~38 tok/s	530K	Open →
NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA · 4.0B params	Q4_K_M	3.46 GB	20.5 GB	~281 tok/s	3.4M	Open →
gemma-4-E2B-itGoogle · 5.1B params	Q4_K_M	4.02 GB	20.0 GB	~653 tok/s	3M	Open →
Qwen3.5-0.8BQwen · 873M params	Q4_K_M	1.46 GB	22.5 GB	~1328 tok/s	2.6M	Open →
Qwen3-VL-8B-InstructQwen · 8.8B params	Q4_K_M	7.04 GB	17.0 GB	~127 tok/s	14.6M	Open →
Qwen3.5-27BQwen · 28B params	Q4_K_M	18.6 GB	5.45 GB	~51 tok/s	1.9M	Open →
North-Micro-Vision-InstructCohereLabs · 2.5B params	Q4_K_M	2.99 GB	21.0 GB	~399 tok/s	180.7K	Open →
Qwen3.5-35B-A3BQwen · 36B params	Q4_K_M	23.1 GB	0.90 GB	~403 tok/s	1.6M	Open →
granite-4.2-8bIBM · 8.8B params	Q4_K_M	7.49 GB	16.5 GB	~116 tok/s	128.4K	Open →
GLM-4.7-Flashzai-org · 31B params	Q4_K_M	20.4 GB	3.59 GB	~38 tok/s	1.8M	Open →
granite-4.1-3bIBM · 3.4B params	Q4_K_M	3.72 GB	20.3 GB	~270 tok/s	521.8K	Open →
LFM2.5-2.6BLiquidAI · 2.7B params	Q4_K_M	2.61 GB	21.4 GB	~433 tok/s	108.1K	Open →
Qwen3-VL-4B-InstructQwen · 4.4B params	Q4_K_M	4.72 GB	19.3 GB	~202 tok/s	3.5M	Open →
granite-4.1-30bIBM · 29B params	Q4_K_M	20.4 GB	3.56 GB	~38 tok/s	301.5K	Open →
Qwen3-VL-2B-InstructQwen · 2.1B params	Q4_K_M	3.05 GB	21.0 GB	~366 tok/s	2.8M	Open →
granite-4.2-3bIBM · 3.7B params	Q4_K_M	3.72 GB	20.3 GB	~270 tok/s	50.6K	Open →
LFM2.5-230MLiquidAI · 230M params	Q4_K_M	1.05 GB	22.9 GB	~3019 tok/s	88.6K	Open →
Qwen3-0.6BQwen · 752M params	Q4_K_M	2.22 GB	21.8 GB	~562 tok/s	29.7M	Open →
gpt-oss-20bOpenAI · 21B params	Q4_K_M	13.8 GB	10.2 GB	~299 tok/s	6.6M	Open →
granite-4.2-30bIBM · 29B params	Q4_K_M	20.7 GB	3.33 GB	~38 tok/s	35.8K	Open →
granite-4.1-8bIBM · 8.8B params	Q4_K_M	7.49 GB	16.5 GB	~116 tok/s	179.3K	Open →
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA · 32B params	Q4_K_M	20.3 GB	3.71 GB	~38 tok/s	875.2K	Open →
LFM2.5-VL-3BLiquidAI · 3.1B params	Q4_K_M	2.85 GB	21.1 GB	~433 tok/s	26.7K	Open →
MiMo-V2.6-Distill-Qwen-9BNEWXiaomiMiMo · 9.4B params	Q4_K_M	6.90 GB	17.1 GB	~154 tok/s	14.6K	Open →
Qwen3-4B-Instruct-2507Qwen · 4.0B params	Q4_K_M	4.72 GB	19.3 GB	~202 tok/s	3.7M	Open →
Ling-3.0-tinyinclusionAI · 7.9B params	Q4_K_M	5.85 GB	18.1 GB	~872 tok/s	17.7K	Open →
Qwen3-8BQwen · 8.2B params	Q4_K_M	7.04 GB	17.0 GB	~127 tok/s	10.7M	Open →
Olmo-3-7B-Instructallenai · 7.3B params	Q4_K_M	7.96 GB	16.0 GB	~108 tok/s	481.7K	Open →
Qwen3-4BQwen · 4.0B params	Q4_K_M	4.51 GB	19.5 GB	~202 tok/s	7.8M	Open →
LFM2.5-8B-A1BLiquidAI · 8.5B params	Q4_K_M	6.06 GB	17.9 GB	~675 tok/s	32.4K	Open →

Sized at the format most people actually download, not at FP16. The catalogue ordered by downloads →

Find the AMD Radeon™ RX 7900 XTX: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.

Under the hood

The specification behind every figure

What the manufacturer publishes for this device, and the pages it was read from.

Manufacturer specification

Memory scope	dedicated
Capacity	24 GB
Published options	24 GB
Bandwidth	960 GB/s
Memory type	GDDR6
Bus width	384-bit
FP32 peak	61.4 TFLOPS
Dense matrix peak	123 TFLOPS (FP16 Matrix, dense)
TBP	355 W

Source ledger

Radeon™ RX 7900 XTX ↗

Retrieved 2026-08-30

Graphics Specifications ↗

Retrieved 2026-08-30

Published capacity is a hardware ceiling, not guaranteed free runtime memory. The calculator shows the runtime reserve separately rather than folding it into a single number.

Run the diagnostic on the AMD Radeon™ RX 7900 XTX →