NVIDIA B200
180 GB decides what fits. 7700 GB/s decides how fast it runs once it does.
- Largest popular model that fitsDeepSeek-V4-Flash284B params · Q4_K_M · needs 175.9 GB~465 tok/s Faster than you readOpen in the calculator →
- Most downloaded that fitsQwen3.8-27B28B params · Q4_K_M · needs 18.6 GB~354 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.
260 of 320 fit entirely
260 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. 10 run with some layers on system memory (32 GB assumed), and 50 do not run at all.
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 | ~4245 tok/s | Open → |
| NVIDIA-Nemotron-3-Nano-4B-BF164.0B parameters | 3.46 GB | fits | ~1967 tok/s | Open → |
| Qwen3-VL-8B-Instruct8.8B parameters | 7.04 GB | fits | ~890 tok/s | Open → |
| Qwen3.5-9B9.7B parameters | 7.05 GB | fits | ~1077 tok/s | Open → |
| gemma-4-12B-it12B parameters | 9.54 GB | fits | ~641 tok/s | Open → |
| gpt-oss-20b21B parameters | 13.8 GB | fits | ~2093 tok/s | Open → |
| Qwen3.8-27B28B parameters | 18.6 GB | fits | ~354 tok/s | Open → |
| Qwen3.6-27B28B parameters | 18.6 GB | fits | ~354 tok/s | Open → |
| Kimi-Linear-48B-A3B-Instruct49B parameters | 30.4 GB | fits | ~2801 tok/s | Open → |
| Qwen3.8-Flash-Next180B parameters | 111.6 GB | fits | ~1455 tok/s | Open → |
| DeepSeek-V4-Flash-Vision-Exp305B parameters | 188.1 GB | 2 of 43 layers on system RAM (8.71 GB) | ~94 tok/s with offload | Open → |
| GLM-5.3-Flash321B parameters | 198.3 GB | 5 of 45 layers on system RAM (21.9 GB) | ~54 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 NVIDIA B200 memory — 260 of 320 sized models
The most demanding model that fits is DeepSeek-V4-Flash at Q4_K_M: 175.9 GB of the 180 GB, leaving 4.12 GB spare.
Fully resident at 8,192 tokens (or the model’s own maximum, where that is shorter), offload off, at 7700 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”.
Showing 40 of 260 models that fit.
| Model | Format | Needs | Spare | Decode | Downloads / 30d | Calculator |
|---|---|---|---|---|---|---|
| Qwen3.8-27BQwen · 28B params | Q4_K_M | 18.6 GB | 161.4 GB | ~354 tok/s | 6.9M | Open → |
| Qwen3.8-Flash-NextNEWQwen · 180B params | Q4_K_M | 111.6 GB | 68.4 GB | ~1455 tok/s | 1.4M | Open → |
| gemma-4-26B-A4B-itGoogle · 26B params | Q4_K_M | 16.8 GB | 163.2 GB | ~1967 tok/s | 13M | Open → |
| gemma-4-31B-itGoogle · 31B params | Q4_K_M | 22.2 GB | 157.8 GB | ~254 tok/s | 9.9M | Open → |
| Qwen3.5-9BQwen · 9.7B params | Q4_K_M | 7.05 GB | 173.0 GB | ~1077 tok/s | 9M | Open → |
| Qwen3.5-4BQwen · 4.7B params | Q4_K_M | 3.98 GB | 176.0 GB | ~1939 tok/s | 7.8M | Open → |
| Qwen3.6-35B-A3BQwen · 36B params | Q4_K_M | 23.1 GB | 156.9 GB | ~2824 tok/s | 3.3M | Open → |
| gemma-4-12B-itGoogle · 12B params | Q4_K_M | 9.54 GB | 170.5 GB | ~641 tok/s | 1.9M | Open → |
| Inkling-Smallthinkingmachines · 266B params | Q4_K_M | 165.5 GB | 14.5 GB | ~735 tok/s | 657.4K | Open → |
| Qwen3.6-27BQwen · 28B params | Q4_K_M | 18.6 GB | 161.4 GB | ~354 tok/s | 2.5M | Open → |
| Qwen3.5-2BQwen · 2.3B params | Q4_K_M | 2.32 GB | 177.7 GB | ~4245 tok/s | 4.9M | Open → |
| gemma-4-E4B-itGoogle · 8.0B params | Q4_K_M | 5.86 GB | 174.1 GB | ~1731 tok/s | 4.4M | Open → |
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA · 32B params | Q4_K_M | 20.3 GB | 159.7 GB | ~268 tok/s | 530K | Open → |
| NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA · 4.0B params | Q4_K_M | 3.46 GB | 176.5 GB | ~1967 tok/s | 3.4M | Open → |
| gemma-4-E2B-itGoogle · 5.1B params | Q4_K_M | 4.02 GB | 176.0 GB | ~4572 tok/s | 3M | Open → |
| Qwen3.5-0.8BQwen · 873M params | Q4_K_M | 1.46 GB | 178.5 GB | ~9299 tok/s | 2.6M | Open → |
| DeepSeek-V4-FlashDeepSeek · 284B params | Q4_K_M | 175.9 GB | 4.12 GB | ~465 tok/s | 1.1M | Open → |
| Qwen3-VL-8B-InstructQwen · 8.8B params | Q4_K_M | 7.04 GB | 173.0 GB | ~890 tok/s | 14.6M | Open → |
| MiniMax-M2.7MiniMaxAI · 229B params | Q4_K_M | 141.2 GB | 38.8 GB | ~609 tok/s | 1.1M | Open → |
| Qwen3.5-27BQwen · 28B params | Q4_K_M | 18.6 GB | 161.4 GB | ~354 tok/s | 1.9M | Open → |
| North-Micro-Vision-InstructCohereLabs · 2.5B params | Q4_K_M | 2.99 GB | 177.0 GB | ~2791 tok/s | 180.7K | Open → |
| Qwen3.5-35B-A3BQwen · 36B params | Q4_K_M | 23.1 GB | 156.9 GB | ~2824 tok/s | 1.6M | Open → |
| NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA · 124B params | Q4_K_M | 76.9 GB | 103.1 GB | ~69 tok/s | 1.2M | Open → |
| granite-4.2-8bIBM · 8.8B params | Q4_K_M | 7.49 GB | 172.5 GB | ~810 tok/s | 128.4K | Open → |
| GLM-4.7-Flashzai-org · 31B params | Q4_K_M | 20.4 GB | 159.6 GB | ~267 tok/s | 1.8M | Open → |
| granite-4.1-3bIBM · 3.4B params | Q4_K_M | 3.72 GB | 176.3 GB | ~1890 tok/s | 521.8K | Open → |
| LFM2.5-2.6BLiquidAI · 2.7B params | Q4_K_M | 2.61 GB | 177.4 GB | ~3032 tok/s | 108.1K | Open → |
| Qwen3-VL-4B-InstructQwen · 4.4B params | Q4_K_M | 4.72 GB | 175.3 GB | ~1414 tok/s | 3.5M | Open → |
| granite-4.1-30bIBM · 29B params | Q4_K_M | 20.4 GB | 159.6 GB | ~266 tok/s | 301.5K | Open → |
| Qwen3.5-122B-A10BQwen · 125B params | Q4_K_M | 77.9 GB | 102.1 GB | ~1034 tok/s | 512.6K | Open → |
| Qwen3-VL-2B-InstructQwen · 2.1B params | Q4_K_M | 3.05 GB | 177.0 GB | ~2563 tok/s | 2.8M | Open → |
| granite-4.2-3bIBM · 3.7B params | Q4_K_M | 3.72 GB | 176.3 GB | ~1890 tok/s | 50.6K | Open → |
| LFM2.5-230MLiquidAI · 230M params | Q4_K_M | 1.05 GB | 178.9 GB | ~21132 tok/s | 88.6K | Open → |
| Qwen3-0.6BQwen · 752M params | Q4_K_M | 2.22 GB | 177.8 GB | ~3932 tok/s | 29.7M | Open → |
| Qwen3-Coder-NextQwen · 80B params | Q4_K_M | 50.0 GB | 130.0 GB | ~1878 tok/s | 596.3K | Open → |
| gpt-oss-20bOpenAI · 21B params | Q4_K_M | 13.8 GB | 166.2 GB | ~2093 tok/s | 6.6M | Open → |
| MiniMax-M2.5MiniMaxAI · 229B params | Q4_K_M | 141.2 GB | 38.8 GB | ~609 tok/s | 444.8K | Open → |
| granite-4.2-30bIBM · 29B params | Q4_K_M | 20.7 GB | 159.3 GB | ~266 tok/s | 35.8K | Open → |
| granite-4.1-8bIBM · 8.8B params | Q4_K_M | 7.49 GB | 172.5 GB | ~810 tok/s | 179.3K | Open → |
| NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA · 32B params | Q4_K_M | 20.3 GB | 159.7 GB | ~268 tok/s | 875.2K | Open → |
Sized at the format most people actually download, not at FP16. The catalogue ordered by downloads →
Rent an B200 by the hour
What the NVIDIA B200 costs on Vast.ai and RunPod right now, per machine, from one card to eight. Every price is read from the provider's own API.
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 specification behind every figure
What the manufacturer publishes for this device, and the pages it was read from.
Manufacturer specification
| Memory scope | dedicated |
|---|---|
| Capacity | 180 GB |
| Published options | 180 GB |
| Bandwidth | 7700 GB/s |
| Memory type | HBM3e |
| Bus width | Not published |
| FP32 peak | Not published |
| Dense matrix peak | Not published without sparsity |
| TDP | 1000 W |
Source ledger
Caveats
- NVIDIA publishes two per-GPU bandwidth figures for the B200: 7.7 TB/s in its exemplar-performance reference architecture and 8 TB/s in its STAC-AI blog ("Each NVIDIA Blackwell B200 GPU includes 180 GB of HBM3e memory and 8 TB/s of memory bandwidth"). The lower figure is used, so the speed estimate cannot be overstated by the choice; the two are not averaged.
- The per-GPU figures come from an 8-GPU HGX reference system; the engine sizes one B200 and splits across up to that count. The DGX system's CPU memory and NVLink Switch fabric are not modelled as device memory.
- No dense matrix throughput is published for this device in a form this catalogue accepts, so no compute roof is priced and time to first token is withheld.
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 NVIDIA B200 →