Runyard is a free hardware-aware AI model browser. You enter your CPU, GPU, and VRAM and it instantly shows every local LLM that will run on your machine, ranked by speed and quality.

How much VRAM do I need to run local LLMs?

8GB of VRAM runs 7B models like Llama 3.1 8B and Mistral 7B at Q4 quantization. 16GB unlocks 13B models. 24GB lets you run Mixtral 8x7B and Llama 3 70B at lower quantization.

What is the best local LLM for my GPU?

Use Runyard at www.runyard.dev — enter your GPU and VRAM and the Model Radar will rank every compatible LLM for your exact hardware, showing estimated tokens per second for each model.

Can I run Llama 3 locally?

Yes. Llama 3.1 8B at Q4 runs on any 8GB VRAM GPU. Llama 3.1 70B needs around 40GB VRAM at Q4, or an Apple Silicon Mac with 64GB+ unified memory.

AMD MI355X Rental Price — $8.60/hr median | GPU Index

AMD MI355X pricing by provider

One card per provider, cheapest first. A configuration is one priced unit — an instance type, a SKU, a marketplace offer — and the per-GPU price is that unit's price divided by its GPU count. Open a card to see every configuration with its vCPU, RAM and region where the provider publishes them.

In stock only1 providers · 1 configurations

Oracle CloudIn stock

USA1 config1xcollected 2026-10-11

On-Demand from $8.60

From

$8.60 / GPU / hr

On-Demand · us-ashburn-1Visit website →

What fits on a AMD MI355X

Weights + KV cache at 8K context + runtime overhead, against 259 GB usable of the 288 GB on the card. Capacity follows total parameters, even for mixture-of-experts models — any expert may be needed next. Where one card is not enough, the table says how many are, and prices the set at today's median.

Model	Params	4-bit	8-bit	16-bit
Kimi K3	2.8T104B active	7× GPU$60.20/hr	12× GPU$103.20/hr	22× GPU$189.20/hr
DeepSeek V4.1-Flash	552B16B active	2× GPU$17.20/hr	3× GPU$25.80/hr	5× GPU$43.00/hr
Llama 4 Maverick	400B17B active	✓ 228 GB~669 tok/s · $3.57/M tok	2× GPU$17.20/hr	4× GPU$34.40/hr
gpt-oss-120b	117B5.1B active	✓ 67.9 GB~2231 tok/s · $1.07/M tok	✓ 126.4 GB~1181 tok/s · $2.02/M tok	✓ 236.1 GB~627 tok/s · $3.81/M tok
Llama 3.1 70B	70B	✓ 44.5 GB~163 tok/s · $14.66/M tok	✓ 79.5 GB~86 tok/s · $27.78/M tok	✓ 145.1 GB~46 tok/s · $51.93/M tok
Gemma 4 31B	31B	✓ 21.2 GB~367 tok/s · $6.51/M tok	✓ 36.7 GB~194 tok/s · $12.31/M tok	✓ 65.7 GB~103 tok/s · $23.19/M tok
Qwen3 Coder 30B-A3B	30.5B3.3B active	✓ 19 GB~3448 tok/s · $0.69/M tok	✓ 34.3 GB~1825 tok/s · $1.31/M tok	✓ 62.9 GB~970 tok/s · $2.46/M tok
Qwen3.8 27B	27B	✓ 18.7 GB~421 tok/s · $5.67/M tok	✓ 32.2 GB~223 tok/s · $10.71/M tok	✓ 57.6 GB~119 tok/s · $20.07/M tok
gpt-oss-20b	21B3.6B active	✓ 13.7 GB~3160 tok/s · $0.76/M tok	✓ 24.2 GB~1673 tok/s · $1.43/M tok	✓ 43.9 GB~889 tok/s · $2.69/M tok
Llama 3.1 8B	8B	✓ 6.9 GB~1422 tok/s · $1.68/M tok	✓ 10.9 GB~753 tok/s · $3.17/M tok	✓ 18.4 GB~400 tok/s · $5.97/M tok

tok/s is decode throughput from memory bandwidth, derated 20%, single stream — an estimate, not a benchmark. $/M tok is the hourly median divided by that rate: the one-user floor for a million generated tokens. Set cost uses today's median × GPUs required.

Specifications

Memory288 GB HBM3e

Memory bandwidth8,000 GB/s

ArchitectureCDNA 4

VendorAMD

ClassDatacenter

Released2025-06

Bandwidth is listed because it governs generation speed: each token streams the active weights once, so tokens per second is bandwidth divided by bytes read. TFLOPs decide prompt processing and training, not how fast text appears.

Questions

How much does it cost to rent a AMD MI355X?

As of 2026-10-11, the median on-demand price across 1 providers is $8.60 per GPU-hour, about $6,192 a month at 720 hours. The cheapest we saw was $8.60 at Oracle Cloud.

Why do prices for the same GPU vary so much?

Hyperscalers bundle CPU, RAM and network into an instance price and charge for the ecosystem around it. Neoclouds sell the GPU more directly. Marketplaces are independent hosts competing on price, with the trade-offs of shared, third-party hardware. The per-GPU figure is the instance price divided by GPU count, which is the only way to compare an 8-GPU node with a single-card listing.

Is the median the price I will pay?

No — it is the middle of the market. Each provider's own median is taken first so a provider with many instance sizes counts once, then the median across providers. Spot and reserved rates are excluded from it; they set the floor shown separately. Use it to judge whether a quote is high or low, then verify with the provider.

Which models can a AMD MI355X run?

With 288 GB per GPU, the table above shows which reference models fit on one card at 4, 8 and 16-bit, using the same memory arithmetic as the rest of Runyard: weights plus KV cache plus runtime overhead, with capacity following total parameters even for mixture-of-experts models. Where a model needs more than one GPU it says how many and what that set costs at today's median.

Own the hardware instead? Work out what your card holds with the same arithmetic.

Check what fits →

AMD MI355X

At a glance

AMD MI355X pricing by provider

What fits on a AMD MI355X

Buy or rent a MI355X?

Specifications

Alternatives and comparisons

Questions