AMD / discrete

AMD Instinct MI300X Accelerator

192 GB decides what fits. 5300 GB/s decides how fast it runs once it does.

Open in the calculator →Best models for 192 GB, on every card that size →

Quick answer

The AMD Instinct MI300X Accelerator fits 265 of 320 sized models entirely in its 192 GB; the largest widely used one is DeepSeek-V4-Flash-Vision-Exp (188.1 GB at Q4_K_M). Memory decides what fits; its 5300 GB/s of bandwidth decides how fast it answers.

Largest popular model that fitsDeepSeek-V4-Flash-Vision-Exp305B params · Q4_K_M · needs 188.1 GB~367 tok/s Faster than you readOpen in the calculator →
Most downloaded that fitsQwen3.8-27B28B params · Q4_K_M · needs 18.6 GB~279 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 Instinct MI300X Accelerator · 192 GB · 5300 GB/s · Q4_K_M where published · 8,192 tokensSpecificationpublished dataDecode speedestimate

265 of 320 fit entirely

265 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. 6 run with some layers on system memory (32 GB assumed), and 49 do not run at all.

83%of the models the engine can size fit entirely

192GB of device memory

5300GB/s memory bandwidth

6run with system memory

49do 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	~3348 tok/s	Open →
NVIDIA-Nemotron-3-Nano-4B-BF164.0B parameters	3.46 GB	fits	~1551 tok/s	Open →
Qwen3-VL-8B-Instruct8.8B parameters	7.04 GB	fits	~702 tok/s	Open →
Qwen3.5-9B9.7B parameters	7.05 GB	fits	~850 tok/s	Open →
gemma-4-12B-it12B parameters	9.54 GB	fits	~505 tok/s	Open →
gpt-oss-20b21B parameters	13.8 GB	fits	~1651 tok/s	Open →
Qwen3.8-27B28B parameters	18.6 GB	fits	~279 tok/s	Open →
Qwen3.6-27B28B parameters	18.6 GB	fits	~279 tok/s	Open →
Kimi-Linear-48B-A3B-Instruct49B parameters	30.4 GB	fits	~2209 tok/s	Open →
Qwen3.8-Flash-Next180B parameters	111.6 GB	fits	~1148 tok/s	Open →
DeepSeek-V4-Flash-Vision-Exp305B parameters	188.1 GB	fits	~367 tok/s	Open →
GLM-5.3-Flash321B parameters	198.3 GB	2 of 45 layers on system RAM (8.77 GB)	~111 tok/s with offload	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 Instinct MI300X Accelerator memory — 265 of 320 sized models

Every model that fitswhole model resident · offload off

The most demanding model that fits is DeepSeek-V4-Flash-Vision-Exp at Q4_K_M: 188.1 GB of the 192 GB, leaving 3.87 GB spare.

Fully resident at 8,192 tokens (or the model’s own maximum, where that is shorter), offload off, at 5300 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 265 models that fit.

Model	Format	Needs	Spare	Decode	Downloads / 30d	Calculator
Qwen3.8-27BQwen · 28B params	Q4_K_M	18.6 GB	173.4 GB	~279 tok/s	6.9M	Open →
DeepSeek-V4-Flash-0731DeepSeek · 304B params	Q4_K_M	187.5 GB	4.48 GB	~367 tok/s	4.5M	Open →
Qwen3.8-Flash-NextNEWQwen · 180B params	Q4_K_M	111.6 GB	80.4 GB	~1148 tok/s	1.4M	Open →
gemma-4-26B-A4B-itGoogle · 26B params	Q4_K_M	16.8 GB	175.2 GB	~1551 tok/s	13M	Open →
DeepSeek-V4-Flash-Vision-ExpNEWDeepSeek · 305B params	Q4_K_M	188.1 GB	3.87 GB	~367 tok/s	915.3K	Open →
gemma-4-31B-itGoogle · 31B params	Q4_K_M	22.2 GB	169.8 GB	~201 tok/s	9.9M	Open →
Qwen3.5-9BQwen · 9.7B params	Q4_K_M	7.05 GB	185.0 GB	~850 tok/s	9M	Open →
Qwen3.5-4BQwen · 4.7B params	Q4_K_M	3.98 GB	188.0 GB	~1529 tok/s	7.8M	Open →
Qwen3.6-35B-A3BQwen · 36B params	Q4_K_M	23.1 GB	168.9 GB	~2227 tok/s	3.3M	Open →
gemma-4-12B-itGoogle · 12B params	Q4_K_M	9.54 GB	182.5 GB	~505 tok/s	1.9M	Open →
Inkling-Smallthinkingmachines · 266B params	Q4_K_M	165.5 GB	26.5 GB	~580 tok/s	657.4K	Open →
Qwen3.6-27BQwen · 28B params	Q4_K_M	18.6 GB	173.4 GB	~279 tok/s	2.5M	Open →
Qwen3.5-2BQwen · 2.3B params	Q4_K_M	2.32 GB	189.7 GB	~3348 tok/s	4.9M	Open →
gemma-4-E4B-itGoogle · 8.0B params	Q4_K_M	5.86 GB	186.1 GB	~1365 tok/s	4.4M	Open →
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA · 32B params	Q4_K_M	20.3 GB	171.7 GB	~212 tok/s	530K	Open →
NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA · 4.0B params	Q4_K_M	3.46 GB	188.5 GB	~1551 tok/s	3.4M	Open →
gemma-4-E2B-itGoogle · 5.1B params	Q4_K_M	4.02 GB	188.0 GB	~3606 tok/s	3M	Open →
Qwen3.5-0.8BQwen · 873M params	Q4_K_M	1.46 GB	190.5 GB	~7334 tok/s	2.6M	Open →
DeepSeek-V4-FlashDeepSeek · 284B params	Q4_K_M	175.9 GB	16.1 GB	~367 tok/s	1.1M	Open →
Qwen3-VL-8B-InstructQwen · 8.8B params	Q4_K_M	7.04 GB	185.0 GB	~702 tok/s	14.6M	Open →
MiniMax-M2.7MiniMaxAI · 229B params	Q4_K_M	141.2 GB	50.8 GB	~481 tok/s	1.1M	Open →
Qwen3.5-27BQwen · 28B params	Q4_K_M	18.6 GB	173.4 GB	~279 tok/s	1.9M	Open →
North-Micro-Vision-InstructCohereLabs · 2.5B params	Q4_K_M	2.99 GB	189.0 GB	~2201 tok/s	180.7K	Open →
Hy3Tencent · 299B params	Q4_K_M	181.2 GB	10.8 GB	~292 tok/s	304.9K	Open →
Qwen3.5-35B-A3BQwen · 36B params	Q4_K_M	23.1 GB	168.9 GB	~2227 tok/s	1.6M	Open →
NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA · 124B params	Q4_K_M	76.9 GB	115.1 GB	~54 tok/s	1.2M	Open →
granite-4.2-8bIBM · 8.8B params	Q4_K_M	7.49 GB	184.5 GB	~639 tok/s	128.4K	Open →
GLM-4.7-Flashzai-org · 31B params	Q4_K_M	20.4 GB	171.6 GB	~210 tok/s	1.8M	Open →
granite-4.1-3bIBM · 3.4B params	Q4_K_M	3.72 GB	188.3 GB	~1491 tok/s	521.8K	Open →
LFM2.5-2.6BLiquidAI · 2.7B params	Q4_K_M	2.61 GB	189.4 GB	~2391 tok/s	108.1K	Open →
Qwen3-VL-4B-InstructQwen · 4.4B params	Q4_K_M	4.72 GB	187.3 GB	~1115 tok/s	3.5M	Open →
granite-4.1-30bIBM · 29B params	Q4_K_M	20.4 GB	171.6 GB	~210 tok/s	301.5K	Open →
Qwen3.5-122B-A10BQwen · 125B params	Q4_K_M	77.9 GB	114.1 GB	~815 tok/s	512.6K	Open →
Qwen3-VL-2B-InstructQwen · 2.1B params	Q4_K_M	3.05 GB	189.0 GB	~2021 tok/s	2.8M	Open →
granite-4.2-3bIBM · 3.7B params	Q4_K_M	3.72 GB	188.3 GB	~1491 tok/s	50.6K	Open →
LFM2.5-230MLiquidAI · 230M params	Q4_K_M	1.05 GB	190.9 GB	~16667 tok/s	88.6K	Open →
Qwen3-0.6BQwen · 752M params	Q4_K_M	2.22 GB	189.8 GB	~3101 tok/s	29.7M	Open →
Qwen3-Coder-NextQwen · 80B params	Q4_K_M	50.0 GB	142.0 GB	~1481 tok/s	596.3K	Open →
gpt-oss-20bOpenAI · 21B params	Q4_K_M	13.8 GB	178.2 GB	~1651 tok/s	6.6M	Open →
MiniMax-M2.5MiniMaxAI · 229B params	Q4_K_M	141.2 GB	50.8 GB	~481 tok/s	444.8K	Open →

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

Rent it instead

Rent an MI300X by the hour

Neither Vast.ai nor RunPod has a AMD Instinct MI300X Accelerator in stock right now. Stock on both changes by the hour.

Prices · 18:30 UTC, 22 Sept

On-demand prices for the whole machine. Vast hosts below 98% measured reliability are left out; RunPod’s Community Cloud is vetted third-party hosts and its Secure Cloud is data-centre capacity. Every rentable card compared.

Referral links Vast.ai, RunPod and Novita pay us a share of what you spend if you sign up through these buttons. It costs you nothing, and it never decides an order or a recommendation: both are computed from the live price and the speed, and options that pay us nothing are listed and recommended on the same terms. How we rank

The Instinct MI300X, model by model

One page per model: whether it fits this device, at which formats, and how fast.

All 14Fewer

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	192 GB
Published options	192 GB
Bandwidth	5300 GB/s
Memory type	HBM3
Bus width	8192-bit
FP32 peak	163.4 TFLOPS
Dense matrix peak	1300 TFLOPS (FP16, dense)
Typical Board Power (TBP), peak	750 W

Source ledger

AMD Instinct MI300X Accelerators ↗

Retrieved 2026-08-30

AMD Instinct MI300X Data Sheet ↗

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 Instinct MI300X Accelerator →