VRAM
192 GB
TDP
1000 W
MSRP
$40k
Perf/W
0.14 x RT/W
Cost/1K tok
$0.0031/k
Tested
2024-12-26
NVIDIA B200 192GB has a source-attributed result of 138.0 tok/s on Llama 3 70B Q4 (batch 1, 8192-token context, Q4_K_M; runtime not documented). This is a reference report, not an independently verified lab result. A 70B Q4_K_M artifact needs roughly 40GB for weights alone; smaller memory configurations require explicit offload or model splitting and do not establish full-GPU residency.
NVIDIA B200 192GB — Blackwell-architecture datacenter GPU. 192GB HBM3e at 8 TB/s, 1000W TDP. Second-gen Transformer Engine with FP4 support. 2.5x the AI compute of H100. NVIDIA's 2025 flagship datacenter GPU.
192GB supports many 70B FP16 configurations after accounting for runtime and cache. 405B FP8 weights require about 405GB; standard 405B Q4 also exceeds 192GB before overhead. Use a documented multi-device configuration for those targets.
NVIDIA B200 192GB with 192GB VRAM at 1000W TDP, scored across 12 workloads with 14 benchmark records.
Reference workload
Whisper transcription
210 x RT
Quantization
FP16
· batch 1
| Workload | Score | Quant | Context | σ | Status | Tested |
|---|---|---|---|---|---|---|
| Llama 3 70B Q4 llm | 138.0tok/s | Q4_K_M | 8K | , | Curated Aggregate | 2024-12-26 |
| Llama 3 70B Q8 llm | 98.0tok/s | Q8_0 | 8K | , | Curated Aggregate | 2024-12-30 |
| Llama 3 8B FP16 llm | 520.0tok/s | FP16 | 8K | , | Curated Aggregate | 2026-02-04 |
| SDXL image gen image | 52.0img/min | FP16 | , | , | Curated Aggregate | 2025-04-15 |
| Qwen 2.5 14B llm | 285.0tok/s | Q4_K_M | 8K | , | Curated Aggregate | 2026-01-15 |
| DeepSeek-R1 7B llm | 480.0tok/s | Q4_K_M | 8K | , | Curated Aggregate | 2026-02-04 |
| Whisper transcription audio | 210.0x RT | FP16 | , | , | Curated Aggregate | 2026-02-22 |
| Mistral 7B llm | 415.0tok/s | Q4_K_M | 4K | , | Curated Aggregate | 2025-01-08 |
| Gemma 2 9B llm | 332.0tok/s | Q4_K_M | 8K | , | Curated Aggregate | 2025-02-12 |
| Llama 3 8B Q4 llm | 360.0tok/s | Q4_K_M | 128K | , | Curated Aggregate | 2025-03-20 |
| Embedding throughput embedding | 23500.0emb/s | FP16 | 1K | , | Curated Aggregate | 2025-01-18 |
| Asure 12B llm | 350.0tok/s | Q4_K_M | 8K | , | Curated Aggregate | 2025-05-01 |
There is insufficient comparable evidence to score NVIDIA B200 192GB. A score needs results for multiple devices with matching workload, runtime version, quantization, context and batch size.
Planning estimates for 192GB: weights plus at least 2GB or 10% overhead. Actual KV cache depends on model, context and cache format; confirm the artifact before buying.
Trust score
6/10
MyAI rating
Not scored
Runs
Not documented
Freshness
Stale
Source-linked row with explicit verification status.
Record date: 2026-02-22; 199 days old.
Enterprise buying note
Retailer we'd check first
Amazon search plus reseller quotes
For datacenter and accelerator parts, Amazon is useful for spotting live listings, accessories, or used pulls, but serious procurement usually happens through integrators, brokers, or cloud partners.
Enterprise procurement, not retail
This silicon is typically acquired through an authorized OEM partner, system integrator, or hyperscaler reseller. For on-demand access, compare hourly rates at RunPod, Vast.ai, Lambda Labs, or your existing cloud provider before committing to capital expenditure.
There is insufficient comparable evidence for a purchase recommendation. Check model fit, software support and a current seller quote.
Affiliate note: we do not have a device-level ASIN yet, so this opens tagged Amazon search results for the exact product name.