The NVIDIA RTX PRO 4000 Blackwell SFF Edition has 24 GB of GDDR7 memory and draws 70 W. The RTX PRO 6000 Blackwell Max-Q has 96 GB and draws 300 W. The 24 GB card runs open models up to about 32 billion parameters at 4-bit quantization, plus Whisper, SDXL and embedding models. The 96 GB card runs 70B-class models, 120B mixture-of-experts models and video models that need 60 GB or more, and it is the only one of the two that supports Multi-Instance GPU (MIG).

As MassiveGRID GPU dedicated servers the two cost $449.99 and $1,656.15 a month: 3.7 times the price for four times the GPU memory and, by NVIDIA's own rating, about 4.6 times the AI compute. This post sets out the specifications, what fits where, and how to decide. Model sizes and vendor facts were checked on 16 November 2026.

How do the RTX PRO 4000 and RTX PRO 6000 compare on paper?

Both are Blackwell-generation professional cards with ECC memory, FP4 support and 9th-generation NVENC encoders. They differ in almost every number.

SpecificationRTX PRO 4000 Blackwell SFF EditionRTX PRO 6000 Blackwell Max-QRatio
GPU memory24 GB GDDR7 with ECC96 GB GDDR7 with ECC4.0x
Memory bandwidth432 GB/s1,792 GB/s4.1x
AI TOPS (NVIDIA's theoretical FP4 peak)7703,5114.6x
CUDA coresnot stated on NVIDIA's page24,064-
Maximum power70 W300 W4.3x
Multi-Instance GPU (MIG)noyes, up to 4 instances of 24 GB-
Video engines2 NVENC, 2 NVDEC4 NVENC, 4 NVDEC2.0x
Concurrent NVENC sessionsunrestrictedunrestricted-
4:2:2 H.264 and HEVC encode, AV1 encodeyesyes-
Card size2.7 in high, 6.6 in long, half height4.4 in high, 10.5 in long, dual slot-

Two numbers matter most for AI work. Memory decides which models load. Memory bandwidth largely decides how fast a loaded model generates tokens, because every token requires reading the model's weights; at 4.1 times the bandwidth the larger card is not just roomier but faster on the same model. We publish no benchmarks of our own, so measure with your model: the same quantization and prompt on both, tokens per second for one request and for your expected concurrency.

The "AI TOPS" figure is, per NVIDIA's footnotes, a theoretical peak of FP4 operations with sparsity. Use it to rank cards within the family, not to predict throughput.

What fits in 24 GB and what needs 96 GB?

The sizes below are the default download sizes on Ollama (4-bit quantization unless noted). A model needs its download size in GPU memory plus working memory for the context, so "fits" here means the download leaves at least 10% of the card free. Larger context windows need more.

Model (Ollama tag)Default size24 GB card96 GB card
llama3.1:8b4.9 GByesyes
gemma4:12b8.0 GByesyes
phi4 (14B)9.1 GByesyes
gpt-oss:20b14 GByesyes
mistral-small3.2 (24B)15 GByesyes
qwen3.8:27b18 GByesyes, also at 8-bit (30 GB) or full precision (56 GB)
gemma4:31b, qwen3:32b, deepseek-r1:32b20 GByes, with a modest contextyes
qwen3.6:35b23 GBtoo tightyes
llama3.3:70b, deepseek-r1:70b43 GBnoyes
gpt-oss:120b65 GBnoyes
llama4:scout67 GBnoyes
devstral-2 (123B)75 GBnoyes
mistral-medium-3.5 (128B), qwen3.5:122b80 GB, 81 GBnoyes, with a limited context
qwen3:235b142 GBnono (needs the four-card server)

Beyond language models:

Context length changes the picture on the small card. Ollama picks its default context from the GPU's memory: 4k tokens below 24 GiB, 32k from 24 to 48 GiB and 256k at 48 GiB or more. A 24 GB card sits on the boundary of the first two tiers, so check what you got with ollama ps and set OLLAMA_CONTEXT_LENGTH yourself. Ollama's documentation recommends at least 64,000 tokens for agents and coding tools, and notes that a larger context increases the memory a model needs. On a 20 GB model in 24 GB there is little room for that. The LLM VRAM requirements guide goes deeper.

What does MIG add, and why is it only on the 6000?

Multi-Instance GPU divides one physical card into isolated instances, each with its own memory, cache and compute cores. NVIDIA's supported-GPU list includes the RTX PRO 6000 Blackwell with up to four instances, and does not include the RTX PRO 4000. On the 6000 the profiles are four instances of 24 GB (1g.24gb), two of 48 GB (2g.48gb) or the whole card.

That makes one 96 GB server usable as four 24 GB GPUs: a chat model, an embedding service, a Whisper endpoint and a development slot that cannot starve each other of memory. Divided by four, the $1,656.15 server is $414.04 per 24 GB slice, less than the $449.99 of the 24 GB server. The comparison is not like for like, though. Four slices share one CPU, one pool of 128 GB RAM and one machine, while each RTX PRO 4000 server is a complete, separate computer. If the four services belong to four customers or must fail independently, separate servers are the cleaner design.

MIG needs some preparation on the workstation editions: driver 575.51.03 or later, a minimum vBIOS, and switching the card from graphics to compute mode with NVIDIA's DisplayModeSelector tool. MIG mode does not persist across a reboot, so it is re-applied at boot. The steps are in splitting an RTX PRO 6000 with MIG.

What are the two server configurations and prices?

The cards are not sold alone. Each comes in a bare-metal server that belongs to one customer, with root access, a 1 Gbps port with unlimited traffic and one dedicated IPv4 address, hosted in an ISO 27001 certified data center.

RTX PRO 4000 serverRTX PRO 6000 serverRatio
Monthly price$449.99$1,656.153.7x
One-time setup fee$346.48$1,656.154.8x
First month in total$796.47$3,312.304.2x
Hourly equivalent (730 hours)$0.62$2.273.7x
Per GB of GPU memory per month$18.75$17.250.92x
GPURTX PRO 4000 Blackwell SFF, 24 GBRTX PRO 6000 Blackwell Max-Q, 96 GB4.0x memory
CPUIntel Core i5-13500, 14 cores / 20 threadsIntel Core Ultra 7 265, 20 cores / 20 threads-
System memory64 GB DDR4128 GB DDR52.0x
Storage2x 512 GB NVMe2x 1.92 TB NVMe Gen4, data-center grade3.75x

Per gigabyte of GPU memory the larger server is slightly less expensive, and it brings twice the system memory and 3.75 times the storage. Storage is worth a moment's thought: mirrored with RAID 1, the smaller server has 512 GB usable, which holds a dozen 20 GB models but fills quickly with image and video checkpoints. A dedicated server is a single machine, so mirroring the two drives and keeping off-server backups is your job on either one.

For context, these are on-demand prices for the same memory classes at four large clouds, checked on 16 November 2026, with the cost of a 730-hour month and the hours a month at which the dedicated server becomes the lower bill.

On-demand instanceGPUPer hour730-hour monthBreak-even hours
Google Cloud g2-standard-4, IowaL4, 24 GB$0.7068$515.99637
AWS g6.xlarge, us-east-1L4, 24 GB$0.8048$587.50559
AWS g5.xlarge, us-east-1A10G, 24 GB$1.006$734.38447
Oracle Cloud VM.GPU.A10.1, list priceA10, 24 GB$2.00$1,460.00225
Azure Standard_NV36ads_A10_v5, East USA10, 24 GB$3.20$2,336.00141
AWS g7e.2xlarge, us-east-1RTX PRO 6000 Blackwell, 96 GB$3.36312$2,455.08492
Google Cloud g4-standard-48, IowaRTX PRO 6000 Blackwell, 96 GB$4.49993$3,284.95368
Oracle Cloud, RTX PRO 6000, list priceRTX PRO 6000$4.50$3,285.00368
Azure NC144lds_xl_RTXPRO6000BSE_v6, East USRTX PRO 6000 Blackwell, 96 GB$5.50$4,015.00301

The 24 GB rows are compared with the $449.99 server and the 96 GB rows with the $1,656.15 server. The 24 GB cloud cards are older designs than the RTX PRO 4000 Blackwell, and the instances differ in vCPUs and RAM. Those instances are billed by the hour and can be stopped; ours is billed by the month and cannot. Below the break-even hours in the last column, paying by the hour costs less.

Is the 6000 worth 3.7 times the price?

It is when at least one of these is true:

It is not worth it when your model fits 24 GB with the context you need and one or a few people use it. A 27B or 32B model at 4-bit answers most internal chat, summarisation, classification and extraction tasks, and paying $1,206.16 more each month for memory that sits empty buys nothing. Start small if you are unsure: the difference in the first month alone is $2,515.83.

Which server should you choose for your workload?

WorkloadChooseReason
Private chat for a small team on a 14B to 32B modelRTX PRO 4000, $449.99Models of 9 to 20 GB fit with a working context
Coding assistant on a 24B to 27B model (devstral-small-2 is 15 GB)RTX PRO 4000Fits; raise the context length deliberately
Embeddings and reranking for a RAG stackRTX PRO 4000Embedding models are 0.3 to 5 GB
Whisper transcriptionRTX PRO 4000About 10 GB for large, 6 GB for turbo
SDXL image generationRTX PRO 40006.94 GB checkpoint
Video transcoding with NVENCRTX PRO 4000, or 6000 for more parallel streams2 or 4 encoders, both with unrestricted sessions
Llama 3.3 70B, gpt-oss 120b or other 40 to 80 GB modelsRTX PRO 6000, $1,656.15Do not fit 24 GB
Agents with 64k or longer context on a 30B modelRTX PRO 6000Context memory on top of a 20 GB model
FLUX and video models (Wan 2.2 A14B, HunyuanVideo)RTX PRO 600023.8 GB weights; 60 to 80 GB stated for video
QLoRA fine-tuning of 32B to 70B modelsRTX PRO 600026 to 41 GB minimum per Unsloth
Several services or teams on one cardRTX PRO 6000MIG: 4 x 24 GB or 2 x 48 GB
A few hours of GPU work a monthNeither: rent by the hourA monthly server only pays off when it is busy

The last row is the honest one for occasional use. The GPU server pricing comparison has the break-even hours, and for very large training jobs H100-class cards rented for the duration of the run are the better tool.

What is the upgrade path from 24 GB to 96 GB?

The two are separate machines, so moving up means ordering the larger server and moving your work across. Plan for it from the first day and it takes an afternoon:

  1. Keep the stack reproducible. Run the serving layer in containers with a compose file, and keep configuration in a repository. The same files start on the new server unchanged.
  2. Treat models as downloads, not data. Public weights can be pulled again on the new machine at 1 Gbps. Copy only what is yours: fine-tuned adapters, vector indexes, chat history, uploads.
  3. Test the larger model before you commit. A 96 GB RTX Pro 6000 rents for $2.69 an hour on RunPod Secure Cloud (on demand, checked on 16 November 2026). A few hours there tell you whether a 70B model is worth the step, for less than $20.
  4. Run both for an overlap period, switch DNS or the reverse proxy to the new server, then let the smaller one end with its paid term. Note that the new server carries its own setup fee of $1,656.15.

Above one card, the same RTX PRO 6000 comes in a Xeon configuration with 256 GB of ECC memory (options up to 768 GB) for $2,485.05 a month, and as a four-card server with 384 GB of GPU memory for $5,966.44. The RTX PRO 6000 server page covers those, and the RTX PRO 4000 server page has the full sizing table for the 24 GB machine. Both servers arrive with a clean Linux install; the first-hour driver and Docker guide applies to either.

Frequently Asked Questions

What is the difference between the RTX PRO 4000 and RTX PRO 6000 Blackwell?

Memory, speed and MIG. The RTX PRO 4000 Blackwell SFF Edition has 24 GB of GDDR7, 432 GB/s of memory bandwidth, 770 AI TOPS and a 70 W power draw. The RTX PRO 6000 Blackwell Max-Q has 96 GB, 1,792 GB/s, 3,511 AI TOPS and 300 W, and supports MIG with up to four 24 GB instances.

Can the RTX PRO 4000 run a 70B model?

Not on the GPU. Llama 3.3 70B is a 43 GB download at Ollama's default 4-bit quantization, which exceeds 24 GB. The largest models that fit comfortably are 27B to 32B at 4-bit (18 to 20 GB). For 70B-class models choose the 96 GB card.

Does the RTX PRO 4000 Blackwell support MIG?

No. NVIDIA's MIG supported-GPU list includes the RTX PRO 6000, 5000 and 4500 Blackwell, not the RTX PRO 4000. On the RTX PRO 6000 a card can be divided into four 24 GB or two 48 GB instances.

How much do the two servers cost?

The RTX PRO 4000 server is $449.99 a month with a $346.48 setup fee, and the RTX PRO 6000 server is $1,656.15 a month with a setup fee of the same amount. Both are on the GPU dedicated servers page and can be ordered online. Per GB of GPU memory that is $18.75 and $17.25 a month.

Start with 24 GB for $449.99 per month

The MassiveGRID RTX PRO 4000 server pairs the 24 GB RTX PRO 4000 Blackwell with a 14-core Intel Core i5-13500, 64 GB of memory and 2x 512 GB NVMe for $449.99 per month plus a one-time $346.48 setup fee. It is single-tenant bare metal with root access, a 1 Gbps port with unlimited traffic and a dedicated IPv4 address: enough for 14B to 32B models, Whisper, SDXL and embeddings. When you outgrow it, the 96 GB RTX PRO 6000 server is $1,656.15.

See the RTX PRO 4000 Server

Further Reading