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

A10 vs L4

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.

A10
$0.09/h24 GB · Ampere · 96 available
L4
$0.05/h24 GB · Ada Lovelace · 96 available
Price gap
44%On spot, per GPU-hour
Over 100 h
$4.00Difference for the same GPU-hours
In short

What actually separates them.

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

The L4 costs 44% less per hour

$0.05 against $0.09 on spot — $4.00 of difference over 100 GPU-hours.

Token generation is faster on the A10

600 GB/s against 300 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 L4

480 GB per dollar per hour against 267 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. A10 leads on 3 rows, L4 on 6.

  A10 L4
GPU memoryDecides which models fit at all 24 GB GDDR6 24 GB GDDR6
Memory bandwidthSets token throughput on inference 600 GB/s 300 GB/s
FP16 tensor 125 TFLOPS 121 TFLOPS
FP32 31 TFLOPS 30 TFLOPS
8-bit float (FP8)Halves the memory a model needs, where the stack supports it Not supported Supported
Architecture Ampere (2021) Ada Lovelace (2023)
Board powerLower is cheaper to run at scale — for us, not for your bill 150 W 72 W
GPU-to-GPU linkOnly matters for multi-GPU training PCIe only PCIe only
Node sizes 1×, 2×, 4× 1×, 2×, 4×
Spot price $0.09/h $0.05/h
On-demand price $0.15/h $0.08/h
Memory per dollarGPU memory per $1 of spot time, per hour 267 GB 480 GB
30-day reclaim rateShare of spot instances reclaimed <5% <5%
Available now 96 GPUs 96 GPUs

Specifications come from each vendor's datasheet — linked on the A10 page and the L4 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 A10 24 GB L4 24 GB
Llama 3.1 8B8B parameters FP16 · 16 GB Fits Fits
INT4 · 4 GB Fits Fits
Qwen2.5 32B32B parameters FP16 · 64 GB Needs 4× node Needs 4× node
INT4 · 16 GB Fits Fits
Llama 3.3 70B70B parameters FP16 · 140 GB Needs more than one node Needs more than one node
INT4 · 35 GB Needs 2× node Needs 2× node
Mixtral 8x22B141B parameters FP16 · 282 GB Needs more than one node Needs more than one node
INT4 · 71 GB Needs 4× node Needs 4× node
Cost

The same 100 GPU-hours on each.

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

 A10L4
One hour, spot$0.09$0.05
One day, spot$2.16$1.20
100 GPU-hours, spot$9.00$5.00
100 GPU-hours, on-demand$15.00$8.00
A month, reserved$65.70$43.80

Take the A10 when…

  • Fine-tuning small models — LoRA on 7B–13B models, and full fine-tuning below 3B.
  • Image and video generation — Diffusion pipelines run entirely in memory at this capacity.
  • Anything that can checkpoint — On the spot tier this model is 40% below its own on-demand price, with a 2-minute notice before a reclaim.

Full A10 page

Take the L4 when…

  • Fine-tuning small models — LoRA on 7B–13B models, and full fine-tuning below 3B.
  • Image and video generation — Diffusion pipelines run entirely in memory at this capacity.
  • Anything that can checkpoint — On the spot tier this model is 38% below its own on-demand price, with a 2-minute notice before a reclaim.

Full L4 page

FAQ

A10 or L4?

Which is cheaper, the A10 or the L4?

The L4, at $0.05 per GPU-hour on spot against $0.09 — 44% less. On-demand: $0.08 against $0.15.

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 A10 on capacity (24 GB) and the A10 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 $0.14 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.