datacenter
Thuê AMD MI300.
CDNA 3
192GB VRAM
750W
Where to rent it
All providers carrying this GPU.
No fresh prices yet.
FAQ
Frequently asked.
How much does it cost to rent the AMD MI300?
No provider has listed a AMD MI300 in the last 24 hours, so there is no current price. Listings for older or less common cards come and go; the price history below shows when it was last available.
What AI models can the AMD MI300 run?
With 192 GB it holds a 70B model at INT8/FP8 (about 70 GB of weights) on one card, or at 4-bit with plenty of room for long contexts and many concurrent requests. It can QLoRA fine-tune 70B models. FP16 70B (about 140 GB) needs two cards.
Which models are recommended for the AMD MI300?
85 models in our catalog have a recommended configuration for this card, with the quantization that fits its 192 GB — see the AI models tab.
Why does the AMD MI300 cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the AMD MI300 price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.
AI models
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
Models that run on this GPU.
GPU-count + quantization recommendations covering fine-tuning, inference, and run-it-yourself scenarios on the AMD MI300.
Llama 3.3 70B
by Meta AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
128K tokens
Qwen 2.5 72B
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
73B
Context
128K tokens
DeepSeek R1 Distill Llama 70B
by DeepSeek
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
128K tokens
Llama 3.1 70B
by Meta AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
128K tokens
Code Llama 70B
by Meta AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
16K tokens
?
FP16
Hermes 3 70B
by Nous Research
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
128K tokens
?
FP16
Nous: Hermes 4 70B
by Nous Research
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
131K tokens
Qwen: Qwen2.5 VL 72B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
72B
Context
131K tokens
?
FP16
Sao10K: Llama 3.1 70B Hanami x1
by Sao10k
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
16K tokens
?
FP16
Sao10K: Llama 3.3 Euryale 70B
by Sao10k
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
131K tokens
?
FP16
Magnum v4 72B
by Anthracite Org
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
72B
Context
33K tokens
?
FP16
Sao10K: Llama 3.1 Euryale 70B v2.2
by Sao10k
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
131K tokens
?
FP16
Sao10k: Llama 3 Euryale 70B v2.1
by Sao10k
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
8K tokens
Meta: Llama 3 70B Instruct
by Meta AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
8K tokens
Meta Llama 3.3 70B Instruct Turbo
by Meta AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
131K tokens
Meta Llama 3.1 70B Instruct Turbo
by Meta AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
131K tokens
nim/meta/llama-3.1-70b-instruct
by Meta AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
16K tokens
nim/nvidia/llama-3.1-nemotron-70b-instruct
by Nvidia
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
16K tokens
Cogito V1 Preview Llama 70B
by Deepcogito
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
131K tokens
Cogito V1 Preview Llama 70B Turbo
by Deepcogito
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
131K tokens
Qwen 2 (72B)
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
72B
Context
33K tokens
Qwen2.5 72B
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
72B
Context
131K tokens
Llama 3.1 70B
by Meta AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
131K tokens
Meta Llama 3 70B Instruct Turbo
by Meta AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
8K tokens
nim/meta/llama-3.3-70b-instruct
by Meta AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
16K tokens
Llama 3.1 Nemotron 70B Instruct HF
by Nvidia
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
33K tokens
meta-llama/Llama-3.3-70B-Instruct
by Meta AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
131K tokens
Llama 3.3 70B Instruct FP8 Lora
by Meta AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
131K tokens
Qwen2.5 72B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
72B
Context
33K tokens
Qwen2 72B Instruct
by Togethercomputer
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
72B
Context
33K tokens
Qwen2.5 72B Instruct Turbo
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
72B
Context
131K tokens
Qwen2-VL (72B) Instruct
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
72B
Context
33K tokens
?
FP16
Hermes-3-Llama-3.1-70B
by Nous Research
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
131K tokens
?
FP16
L3.1-70B-Euryale-v2.2
by Sao10k
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
131K tokens
Meta-Llama-3.1-70B-Instruct
by Meta AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
131K tokens
Xiaomi: MiMo-V2.5-Pro
by Xiaomi
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
65B
Context
1M tokens
Writer: Palmyra X5
by Writer
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
1M tokens
?
FP16
Morph: Morph V3 Large
by Morph
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
70B
Context
262K tokens
Mistral Large 2
by Mistral AI
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
123B
Context
128K tokens
Mixtral 8x22B
by Mistral AI
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
141B (39B active)
Context
66K tokens
GPT-OSS 120B
by OpenAI
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
120B (5B active)
Context
128K tokens
NVIDIA: Nemotron 3 Super
by Nvidia
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
120B
Context
1M tokens
Qwen: Qwen3.5-122B-A10B
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
122B
Context
262K tokens
Nvidia Nemotron 3 Super 120B A12b Fp8
by Nvidia
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
120B
Context
262K tokens
Nvidia Nemotron 3 Super 120B A12b Bf16
by Nvidia
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
120B
Context
262K tokens
Qwen3.5 122B A10b Fp8
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
122B
Context
262K tokens
NVIDIA-Nemotron-3-Super-120B-A12B
by Nvidia
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
120B
Context
262K tokens
gpt-oss-120b-Turbo
by OpenAI
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
120B
Context
131K tokens
Mistral: Mistral Small 4
by Mistral AI
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
121B
Context
262K tokens
Mistral: Devstral 2 2512
by Mistral AI
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
128B
Context
262K tokens
Qwen3.5 122B A10B Lora
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
122B
Context
8K tokens
gpt-oss-120b-Ultra
by OpenAI
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
120B
Context
131K tokens
?
FP16
Ling-3.0-flash-VL
by Inclusionai
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
125B
Context
131K tokens
Qwen 3 235B
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
235B (22B active)
Context
128K tokens
DeepSeek Coder V2 236B
by DeepSeek
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
236B (21B active)
Context
128K tokens
Qwen: Qwen3 VL 235B A22B Thinking
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
235B
Context
131K tokens
Qwen: Qwen3 VL 235B A22B Instruct
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
235B
Context
262K tokens
Qwen: Qwen3 235B A22B Thinking 2507
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
235B
Context
262K tokens
Qwen: Qwen3 235B A22B Instruct 2507
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
235B
Context
262K tokens
Qwen: Qwen3 235B A22B
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
235B
Context
131K tokens
Baidu: ERNIE 4.5 300B A47B
by Baidu
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
300B
Context
131K tokens
Qwen3 235B A22B Instruct 2507 FP8 Throughput
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
235B
Context
262K tokens
Qwen3-VL-235B-A22B-Instruct-FP8
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
235B
Context
262K tokens
Qwen3-235B-A22B-Instruct-2507
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
235B
Context
262K tokens
Qwen: Qwen3.5 Plus 2026-04-20
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
235B
Context
1M tokens
Qwen: Qwen3 Max
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
235B
Context
262K tokens
DeepSeek: DeepSeek V4 Flash
by DeepSeek
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
292B
Context
1M tokens
Tencent: Hy3 preview
by Tencent
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
299B
Context
262K tokens
Qwen: Qwen3 Coder 480B A35B
by Alibaba (Qwen Team)
Required GPUs
8× AMD MI300
Total VRAM
1536 GB
Parameters
480B
Context
1M tokens
Qwen3 Coder 480B A35B Instruct Fp8
by Alibaba (Qwen Team)
Required GPUs
8× AMD MI300
Total VRAM
1536 GB
Parameters
480B
Context
262K tokens
Qwen3-Coder-480B-A35B-Instruct-Turbo
by Alibaba (Qwen Team)
Required GPUs
8× AMD MI300
Total VRAM
1536 GB
Parameters
480B
Context
262K tokens
Qwen: Qwen3 Coder Next
by Alibaba (Qwen Team)
Required GPUs
8× AMD MI300
Total VRAM
1536 GB
Parameters
480B
Context
262K tokens
NVIDIA: Nemotron 3 Ultra
by Nvidia
Required GPUs
8× AMD MI300
Total VRAM
1536 GB
Parameters
550B
Context
1M tokens
NVIDIA-Nemotron-3-Ultra-550B-A55B
by Nvidia
Required GPUs
8× AMD MI300
Total VRAM
1536 GB
Parameters
550B
Context
262K tokens
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
by Nvidia
Required GPUs
8× AMD MI300
Total VRAM
1536 GB
Parameters
550B
Context
262K tokens
Mistral Large 2
by Mistral AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
123B
Context
128K tokens
Mixtral 8x22B
by Mistral AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
141B (39B active)
Context
66K tokens
GPT-OSS 120B
by OpenAI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
120B (5B active)
Context
128K tokens
NVIDIA: Nemotron 3 Super
by Nvidia
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
120B
Context
1M tokens
Qwen: Qwen3.5-122B-A10B
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
122B
Context
262K tokens
Nvidia Nemotron 3 Super 120B A12b Fp8
by Nvidia
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
120B
Context
262K tokens
Nvidia Nemotron 3 Super 120B A12b Bf16
by Nvidia
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
120B
Context
262K tokens
Qwen3.5 122B A10b Fp8
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
122B
Context
262K tokens
NVIDIA-Nemotron-3-Super-120B-A12B
by Nvidia
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
120B
Context
262K tokens
gpt-oss-120b-Turbo
by OpenAI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
120B
Context
131K tokens
Mistral: Mistral Small 4
by Mistral AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
121B
Context
262K tokens
Mistral: Devstral 2 2512
by Mistral AI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
128B
Context
262K tokens
Qwen3.5 122B A10B Lora
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
122B
Context
8K tokens
gpt-oss-120b-Ultra
by OpenAI
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
120B
Context
131K tokens
?
FP8
Ling-3.0-flash-VL
by Inclusionai
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
125B
Context
131K tokens
Qwen 3 235B
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
235B (22B active)
Context
128K tokens
DeepSeek Coder V2 236B
by DeepSeek
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
236B (21B active)
Context
128K tokens
Qwen: Qwen3 VL 235B A22B Thinking
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
235B
Context
131K tokens
Qwen: Qwen3 VL 235B A22B Instruct
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
235B
Context
262K tokens
Qwen: Qwen3 235B A22B Thinking 2507
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
235B
Context
262K tokens
Qwen: Qwen3 235B A22B Instruct 2507
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
235B
Context
262K tokens
Qwen: Qwen3 235B A22B
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
235B
Context
131K tokens
Baidu: ERNIE 4.5 300B A47B
by Baidu
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
300B
Context
131K tokens
Qwen3 235B A22B Instruct 2507 FP8 Throughput
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
235B
Context
262K tokens
Qwen3-VL-235B-A22B-Instruct-FP8
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
235B
Context
262K tokens
Qwen3-235B-A22B-Instruct-2507
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
235B
Context
262K tokens
Qwen: Qwen3.5 Plus 2026-04-20
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
235B
Context
1M tokens
Qwen: Qwen3 Max
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
235B
Context
262K tokens
DeepSeek: DeepSeek V4 Flash
by DeepSeek
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
292B
Context
1M tokens
Tencent: Hy3 preview
by Tencent
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
299B
Context
262K tokens
Qwen: Qwen3 Coder 480B A35B
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
480B
Context
1M tokens
Qwen3 Coder 480B A35B Instruct Fp8
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
480B
Context
262K tokens
Qwen3-Coder-480B-A35B-Instruct-Turbo
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
480B
Context
262K tokens
Qwen: Qwen3 Coder Next
by Alibaba (Qwen Team)
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
480B
Context
262K tokens
NVIDIA: Nemotron 3 Ultra
by Nvidia
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
550B
Context
1M tokens
NVIDIA-Nemotron-3-Ultra-550B-A55B
by Nvidia
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
550B
Context
262K tokens
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
by Nvidia
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
550B
Context
262K tokens
?
FP8
Kimi K2
by Moonshot AI
Required GPUs
8× AMD MI300
Total VRAM
1536 GB
Parameters
1000B (32B active)
Context
256K tokens
?
FP8
Kimi K2 Thinking
by Moonshot AI
Required GPUs
8× AMD MI300
Total VRAM
1536 GB
Parameters
1000B (32B active)
Context
256K tokens
?
FP8
Kimi K2.5
by Moonshot AI
Required GPUs
8× AMD MI300
Total VRAM
1536 GB
Parameters
1000B (32B active)
Context
256K tokens
?
FP8
Kimi K2.6
by Moonshot AI
Required GPUs
8× AMD MI300
Total VRAM
1536 GB
Parameters
1000B (32B active)
Context
256K tokens
?
FP8
MoonshotAI Kimi Latest
by Moonshot AI
Required GPUs
8× AMD MI300
Total VRAM
1536 GB
Parameters
1000B
Context
262K tokens
?
FP8
MoonshotAI: Kimi K2 0905
by Moonshot AI
Required GPUs
8× AMD MI300
Total VRAM
1536 GB
Parameters
1000B
Context
262K tokens
?
FP8
Inkling FP4
by Thinking Machines
Required GPUs
8× AMD MI300
Total VRAM
1536 GB
Parameters
952B
Context
524K tokens
Qwen 3 235B
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
235B (22B active)
Context
128K tokens
DeepSeek Coder V2 236B
by DeepSeek
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
236B (21B active)
Context
128K tokens
Qwen: Qwen3 VL 235B A22B Thinking
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
235B
Context
131K tokens
Qwen: Qwen3 VL 235B A22B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
235B
Context
262K tokens
Qwen: Qwen3 235B A22B Thinking 2507
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
235B
Context
262K tokens
Qwen: Qwen3 235B A22B Instruct 2507
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
235B
Context
262K tokens
Qwen: Qwen3 235B A22B
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
235B
Context
131K tokens
Baidu: ERNIE 4.5 300B A47B
by Baidu
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
300B
Context
131K tokens
Qwen3 235B A22B Instruct 2507 FP8 Throughput
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
235B
Context
262K tokens
Qwen3-VL-235B-A22B-Instruct-FP8
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
235B
Context
262K tokens
Qwen3-235B-A22B-Instruct-2507
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
235B
Context
262K tokens
Qwen: Qwen3.5 Plus 2026-04-20
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
235B
Context
1M tokens
Qwen: Qwen3 Max
by Alibaba (Qwen Team)
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
235B
Context
262K tokens
DeepSeek: DeepSeek V4 Flash
by DeepSeek
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
292B
Context
1M tokens
Tencent: Hy3 preview
by Tencent
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
299B
Context
262K tokens
MiniMax: MiniMax M2.7
by MiniMax
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
230B
Context
205K tokens
MiniMax: MiniMax M2.5
by MiniMax
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
230B
Context
205K tokens
MiniMax: MiniMax M2.1
by MiniMax
Required GPUs
1× AMD MI300
Total VRAM
192 GB
Parameters
230B
Context
205K tokens
Qwen: Qwen3 Coder 480B A35B
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
480B
Context
1M tokens
Qwen3 Coder 480B A35B Instruct Fp8
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
480B
Context
262K tokens
Qwen3-Coder-480B-A35B-Instruct-Turbo
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
480B
Context
262K tokens
Qwen: Qwen3 Coder Next
by Alibaba (Qwen Team)
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
480B
Context
262K tokens
NVIDIA: Nemotron 3 Ultra
by Nvidia
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
550B
Context
1M tokens
NVIDIA-Nemotron-3-Ultra-550B-A55B
by Nvidia
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
550B
Context
262K tokens
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
by Nvidia
Required GPUs
2× AMD MI300
Total VRAM
384 GB
Parameters
550B
Context
262K tokens
?
INT4
Kimi K2
by Moonshot AI
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
1000B (32B active)
Context
256K tokens
?
INT4
Kimi K2 Thinking
by Moonshot AI
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
1000B (32B active)
Context
256K tokens
?
INT4
Kimi K2.5
by Moonshot AI
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
1000B (32B active)
Context
256K tokens
?
INT4
Kimi K2.6
by Moonshot AI
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
1000B (32B active)
Context
256K tokens
?
INT4
MoonshotAI Kimi Latest
by Moonshot AI
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
1000B
Context
262K tokens
?
INT4
MoonshotAI: Kimi K2 0905
by Moonshot AI
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
1000B
Context
262K tokens
?
INT4
Inkling FP4
by Thinking Machines
Required GPUs
4× AMD MI300
Total VRAM
768 GB
Parameters
952B
Context
524K tokens
Renting for inference?
Pair these models with the cheapest provider on the rental table.
See rental rates on the Overview tab →
FAQ
AI models on this GPU.
How much does it cost to rent the AMD MI300?
No provider has listed a AMD MI300 in the last 24 hours, so there is no current price. Listings for older or less common cards come and go; the price history below shows when it was last available.
What AI models can the AMD MI300 run?
With 192 GB it holds a 70B model at INT8/FP8 (about 70 GB of weights) on one card, or at 4-bit with plenty of room for long contexts and many concurrent requests. It can QLoRA fine-tune 70B models. FP16 70B (about 140 GB) needs two cards.
Which models are recommended for the AMD MI300?
85 models in our catalog have a recommended configuration for this card, with the quantization that fits its 192 GB — see the AI models tab.
Why does the AMD MI300 cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the AMD MI300 price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.