New B200 spot capacity is live in US East from $1.69 per GPU-hour. See availability
Comparison

RTX A6000 vs RTX A4500

Both run on the same nodes, the same templates and the same tiers here — so the choice comes down to memory, bandwidth and price. Every figure below is from the catalogue or the vendor datasheet.

RTX A6000
$0.09/h48 GB · Ampere · 48 available
RTX A4500
$0.06/h20 GB · Ampere · 16 available
Price gap
33%On spot, per GPU-hour
Over 100 h
$3.00Difference for the same GPU-hours
In short

What actually separates them.

Four differences that change a decision, computed from the numbers rather than asserted.

Bigger models fit on the RTX A6000

48 GB against 20 GB. At FP16 that is about 19B parameters on one GPU, against 8B.

The RTX A4500 costs 33% less per hour

$0.06 against $0.09 on spot — $3.00 of difference over 100 GPU-hours.

Token generation is faster on the RTX A6000

768 GB/s against 640 GB/s. Inference reads the whole model from memory for every token, so bandwidth, not FLOPS, usually sets the ceiling.

More memory per dollar on the RTX A6000

533 GB per dollar per hour against 333 GB. The usual tie-breaker when both cards fit the job.

Side by side

Every figure we hold on both cards.

A row is marked only when both values exist and one is genuinely better. RTX A6000 leads on 5 rows, RTX A4500 on 4.

  RTX A6000 RTX A4500
GPU memoryDecides which models fit at all 48 GB GDDR6 20 GB GDDR6
Memory bandwidthSets token throughput on inference 768 GB/s 640 GB/s
FP32 39 TFLOPS 24 TFLOPS
8-bit float (FP8)Halves the memory a model needs, where the stack supports it Not supported Not supported
Architecture Ampere (2020) Ampere (2021)
Board powerLower is cheaper to run at scale — for us, not for your bill 300 W 200 W
GPU-to-GPU linkOnly matters for multi-GPU training NVLink NVLink
Node sizes 1×, 2×, 4× 1×, 2×, 4×
Spot price $0.09/h $0.06/h
On-demand price $0.17/h $0.09/h
Memory per dollarGPU memory per $1 of spot time, per hour 533 GB 333 GB
30-day reclaim rateShare of spot instances reclaimed <5% <5%
Available now 48 GPUs 16 GPUs

Specifications come from each vendor's datasheet — linked on the RTX A6000 page and the RTX A4500 page. Prices are ours, per GPU-hour, billed per minute.

What fits

The same models, on one GPU of each.

Weights only, with 20% of the memory kept free for activations and the KV cache. A cross means one GPU is not enough — the model page has the multi-GPU arithmetic.

Model Precision RTX A6000 48 GB RTX A4500 20 GB
Llama 3.1 8B8B parameters FP16 · 16 GB Fits Fits
INT4 · 4 GB Fits Fits
Qwen2.5 32B32B parameters FP16 · 64 GB Needs 2× node Needs 4× node
INT4 · 16 GB Fits Fits
Llama 3.3 70B70B parameters FP16 · 140 GB Needs 4× node Needs more than one node
INT4 · 35 GB Fits Needs 4× node
Mixtral 8x22B141B parameters FP16 · 282 GB Needs more than one node Needs more than one node
INT4 · 71 GB Needs 2× node Needs more than one node
Cost

The same 100 GPU-hours on each.

Compute only, billed per minute. Storage is $0.08 per GB-month on either card.

 RTX A6000RTX A4500
One hour, spot$0.09$0.06
One day, spot$2.16$1.44
100 GPU-hours, spot$9.00$6.00
100 GPU-hours, on-demand$17.00$9.00
A month, reserved$65.70$43.80

Take the RTX A6000 when…

  • Fine-tuning with LoRA and QLoRA — Comfortable for parameter-efficient training on 13B–34B models without sharding.
  • Inference servers — Holds 30B-class models quantised, or several smaller models side by side.
  • Multi-GPU jobs over NVLink — GPU-to-GPU traffic stays off the PCIe bus, which is what makes tensor and pipeline parallelism worth it.

Full RTX A6000 page

Take the RTX A4500 when…

  • Quantised inference — Small and medium models in 4-bit or 8-bit form, with the whole model resident in memory.
  • Computer vision and batch jobs — Detection, classification, embeddings and transcoding at a very low hourly rate.
  • Multi-GPU jobs over NVLink — GPU-to-GPU traffic stays off the PCIe bus, which is what makes tensor and pipeline parallelism worth it.

Full RTX A4500 page

FAQ

RTX A6000 or RTX A4500?

Which is cheaper, the RTX A6000 or the RTX A4500?

The RTX A4500, at $0.06 per GPU-hour on spot against $0.09 — 33% less. On-demand: $0.09 against $0.17.

Which one should I take for inference?

Take the one that holds the model with room for the KV cache, then the one with more memory bandwidth. Here that is the RTX A6000 on capacity (48 GB) and the RTX A6000 on bandwidth.

Can I run both on the same job?

Not inside one instance — a node holds GPUs of a single model. You can run two instances in parallel, on the same persistent volume in turn, or split the work: a big card for the model that needs capacity, a cheap one for the parts that do not.

Other comparisons: the full list · all 47 models

Get started

Try both for less than the price of deciding.

An hour on each costs $0.15 on spot. Nothing renews, and your disk moves between them.

Billed per minute from the moment the instance is reachable. Minimum credit $40, no subscription.