datacenter
Nvidia B300 MIG 34GB mieten.
Blackwell
34GB VRAM
Price history
Daily median across providers.
Loading...
Where to rent it
All providers carrying this GPU.
No fresh prices yet.
FAQ
Frequently asked.
How is the Nvidia B300 MIG 34GB price calculated?
We pull live listings from each provider's public API, take the median hourly rate across active offers, and refresh every hour. The rate shown is the median, so a single low-ball spot offer can't distort the headline.
Why does the Nvidia B300 MIG 34GB cost different amounts on different providers?
P2P marketplaces like Vast.ai aggregate offers from individual hosts who set their own rates — bidding pushes prices down. First-party clouds (Lambda, hyperscalers) charge a managed-service premium for support, SLAs, and integrated networking. Decentralized networks (io.net, Akash) settle in tokens, which adds volatility but often the lowest base rate.
Can I really train an LLM on a single Nvidia B300 MIG 34GB?
Depends on the model size. With 34GB of VRAM you can fine-tune 13B–34B models with LoRA, or run inference on 70B models at int4 quantization.
Spot vs on-demand on the Nvidia B300 MIG 34GB — which should I rent?
On-demand keeps the same instance until you stop it; spot (or interruptible) is cheaper but the host can reclaim it when a higher-paying job lands. Use on-demand for training runs and anything stateful. Use spot for stateless inference, batch jobs, and experiments where a checkpoint every few minutes is enough to recover.
How is hourly billing measured for the Nvidia B300 MIG 34GB?
Most providers bill per-second once the instance is running, with a small minimum (often 60 seconds). A handful of first-party clouds round up to the minute. Either way, headline $/hr is the right comparison unit.
Does the region of the host affect the Nvidia B300 MIG 34GB price?
Yes — US and EU regions usually carry a premium over LATAM, India, and parts of APAC, especially on first-party clouds. P2P marketplaces hide this behind one global price because supply moves wherever bids exist.
AI models
INT4
INT4
FP16
FP16
FP16
INT4
INT4
INT4
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
Models that run on this GPU.
GPU-count + quantization recommendations covering fine-tuning, inference, and run-it-yourself scenarios on the Nvidia B300 MIG 34GB.
nim/nvidia/llama-3.3-nemotron-super-49b-v1
by Nvidia
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
49B
Context
16K tokens
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5
by Nvidia
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
49B
Context
131K tokens
LLaVA 13B
by LLaVA Project
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
13B
Context
4K tokens
Code Llama 13B
by Meta AI
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
13B
Context
16K tokens
Baichuan2-13B
by Baichuan Inc.
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
13B
Context
4K tokens
?
FP16
ReMM SLERP 13B
by Undi95
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
13B
Context
6K tokens
?
FP16
MythoMax 13B
by Gryphe
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
13B
Context
4K tokens
?
INT4
TheDrummer: Skyfall 36B V2
by Thedrummer
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
36B
Context
33K tokens
Qwen: Qwen3.5-35B-A3B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
35B
Context
262K tokens
Qwen3.6 35B A3b Fp8
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
35B
Context
262K tokens
Qwen: Qwen3.6 35B A3B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
35B
Context
262K tokens
Gemma 3 27B
by Google DeepMind
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
27B (27B active)
Context
128K tokens
Gemma 2 27B
by Google DeepMind
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
27B
Context
8K tokens
Qwen: Qwen3.6 27B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
27B
Context
262K tokens
Qwen: Qwen3.5-27B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
27B
Context
262K tokens
Gemma 3 27B It
by Google DeepMind
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
27B
Context
66K tokens
Gemma 3 27B Pt
by Google DeepMind
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
27B
Medgemma 27B Text It
by Google DeepMind
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
27B
Context
131K tokens
Gemma 3 27B It Lora
by Google DeepMind
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
27B
Qwen3.5 27B Lora
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
27B
Context
262K tokens
Qwen3.6 27B Lora
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
27B
Context
262K tokens
?
FP8
Ternary Bonsai 27B
by Prism ML
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
27B
Context
262K tokens
Qwen: Qwen3.8 27B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia B300 MIG 34GB
Total VRAM
34 GB
Parameters
27B
Context
262K 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 is the Nvidia B300 MIG 34GB price calculated?
We pull live listings from each provider's public API, take the median hourly rate across active offers, and refresh every hour. The rate shown is the median, so a single low-ball spot offer can't distort the headline.
Why does the Nvidia B300 MIG 34GB cost different amounts on different providers?
P2P marketplaces like Vast.ai aggregate offers from individual hosts who set their own rates — bidding pushes prices down. First-party clouds (Lambda, hyperscalers) charge a managed-service premium for support, SLAs, and integrated networking. Decentralized networks (io.net, Akash) settle in tokens, which adds volatility but often the lowest base rate.
Can I really train an LLM on a single Nvidia B300 MIG 34GB?
Depends on the model size. With 34GB of VRAM you can fine-tune 13B–34B models with LoRA, or run inference on 70B models at int4 quantization.
Spot vs on-demand on the Nvidia B300 MIG 34GB — which should I rent?
On-demand keeps the same instance until you stop it; spot (or interruptible) is cheaper but the host can reclaim it when a higher-paying job lands. Use on-demand for training runs and anything stateful. Use spot for stateless inference, batch jobs, and experiments where a checkpoint every few minutes is enough to recover.
How is hourly billing measured for the Nvidia B300 MIG 34GB?
Most providers bill per-second once the instance is running, with a small minimum (often 60 seconds). A handful of first-party clouds round up to the minute. Either way, headline $/hr is the right comparison unit.
Does the region of the host affect the Nvidia B300 MIG 34GB price?
Yes — US and EU regions usually carry a premium over LATAM, India, and parts of APAC, especially on first-party clouds. P2P marketplaces hide this behind one global price because supply moves wherever bids exist.