LLMBOTTLENECK.COM
inclusionAI / llada2_moe

LLaDA2.0-mini

16.3 billion parameters, routing 8 of 256 experts per token.

Open in the calculator →

Architecturepublished data
Quick answer
LLaDA2.0-mini needs about 11.0 GB at Q4_K_M — the format most people download — with 8,192 tokens of context. It fits entirely on 18 of 18 common devices, starting with the NVIDIA GeForce RTX 5070 (12 GB). What else fits in 12 GB. No hardware for it? Rent a GPU that runs it, priced live.

Sized at 8,192 tokens of context with the whole model in device memory, across 18 common devices. Speeds are estimates, not benchmarks.

Find the NVIDIA GeForce RTX 5070, the smallest card listed here that holds it: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.

Weight-file size by format

FormatSizeRangeBasis
FP1632.4 GB31.8 GB – 32.7 GBreconstructed size
Q8_017.2 GB16.9 GB – 17.4 GBreconstructed size
Q6_K13.3 GB13.1 GB – 13.4 GBreconstructed size
Q5_K_M11.5 GB11.3 GB – 11.6 GBreconstructed size
Q5_011.2 GB10.9 GB – 11.3 GBreconstructed size
Q4_K_M9.86 GB9.59 GB – 9.95 GBreconstructed size
Q4_09.23 GB8.96 GB – 9.32 GBreconstructed size
Q3_K_M8.11 GB7.52 GB – 8.71 GBreconstructed size
Q2_K6.04 GB5.77 GB – 6.30 GBreconstructed size

A file size is not the memory a run needs: the KV cache and the runtime reserve come on top, and the calculator adds both.

What the labels mean
published data
Read from a published source — a file's byte count, a model's configuration or a manufacturer's specification — or exact arithmetic on such values. Not a measurement on a machine.
reconstructed size
Weight size reconstructed from the pinned architecture, because no published file exists.
size range
Only a lower and an upper bound are claimed for this weight size.

Hardware ladder

Q4_K_M at 8,192 tokens · 18 of 18 devices hold it entirely
DeviceMemoryVerdictDecodeCalculator
NVIDIA GeForce RTX 507011.0 GB of 12 GBfits~427 tok/sOpen →
AMD Radeon™ RX 9070 XT11.0 GB of 16 GBfits~466 tok/sOpen →
NVIDIA GeForce RTX 408011.0 GB of 16 GBfits~455 tok/sOpen →
NVIDIA GeForce RTX 508011.0 GB of 16 GBfits~610 tok/sOpen →
NVIDIA GeForce RTX 5070 Ti11.0 GB of 16 GBfits~569 tok/sOpen →
NVIDIA GeForce RTX 5060 Ti 16GB11.0 GB of 16 GBfits~285 tok/sOpen →
NVIDIA GeForce RTX 409011.0 GB of 24 GBfits~640 tok/sOpen →
AMD Radeon™ RX 7900 XTX11.0 GB of 24 GBfits~699 tok/sOpen →
NVIDIA GeForce RTX 309011.0 GB of 24 GBfits~595 tok/sOpen →
NVIDIA GeForce RTX 509011.0 GB of 32 GBfits~1138 tok/sOpen →
NVIDIA RTX 6000 Ada Generation11.0 GB of 48 GBfits~610 tok/sOpen →
Apple M4 Pro11.0 GB of 64 GBfits~101 tok/sOpen →
Apple M5 Pro11.0 GB of 64 GBfits~106 tok/sOpen →
AMD Ryzen AI Max+ 395 with Radeon 8060S11.0 GB of 128 GBfits~186 tok/sOpen →
Apple M3 Max11.0 GB of 128 GBfits~117 tok/sOpen →
Apple M4 Max11.0 GB of 128 GBfits~129 tok/sOpen →
NVIDIA DGX Spark11.0 GB of 128 GBfits~173 tok/sOpen →
Apple M2 Ultra11.0 GB of 192 GBfits~141 tok/sOpen →

Decode is a calibrated estimate from the published calibration; capacity is the manufacturer's published ceiling, not guaranteed free memory. Fitting in memory is not the same as loading: whether the runtime and version you have supports this architecture and format on that machine has not been tested here. Offloaded rows assume there is enough system RAM for the overflow — the calculator checks that against the RAM you declare. Each “Open” link keeps this model, format and context.

Run it in the cloud

Rent a GPU that runs LLaDA2.0-mini

Every rentable machine that holds the whole model, from Vast.ai and RunPod, with this site's speed estimate for each and the provider's own price, read live. Cheapest first; sort by cost per token or speed instead, or switch the format.

Prices · 18:30 UTC, 22 Sept
28 configurations in stock · 5 out of stock
MachineSpeedPer hourPer M tokensWhereRent
1× RTX 306012 GBrecommendedcheapestbest value~228 tok/sFaster than you read$0.036$0.043Vast.aiMarketplace · 99.8% reliableRent on Vast.ai
1× RTX 4060 Ti 16GB16 GB~183 tok/sFaster than you read$0.090$0.14Vast.aiMarketplace · 99.4% reliableRent on Vast.ai
1× RTX 407012 GB~320 tok/sFaster than you read$0.096$0.083Vast.aiMarketplace · 99.8% reliableRent on Vast.ai
1× RTX 309024 GB~594 tok/sFaster than you read$0.12$0.057Vast.aiMarketplace · 99.5% reliableRunPod $0.50/h Rent on Vast.ai
1× RTX 5060 Ti 16GB16 GB~284 tok/sFaster than you read$0.12$0.12Vast.aiMarketplace · 99.1% reliableRent on Vast.ai
1× RTX 3080 Ti12 GB~579 tok/sFaster than you read$0.14$0.065Vast.aiMarketplace · 99.9% reliableRent on Vast.ai
1× RTX 507012 GB~426 tok/sFaster than you read$0.18$0.11Vast.aiMarketplace · 98.3% reliableRent on Vast.ai
1× RTX 3090 Ti24 GB~640 tok/sFaster than you read$0.19$0.081Vast.aiMarketplace · 99.6% reliableRunPod $0.27/h Rent on Vast.ai

First time renting a GPU? How it works, in four steps
  1. Create an account and add credit. Both providers are prepaid: $10 is enough to try any card on this page for hours. A new RunPod account that arrives through a referral link gets a one-time $5 credit when it first adds $10.
  2. Pick the card and the count shown here, and a template: llama.cpp or vLLM for an OpenAI-compatible API, or one with a web chat if you only want to talk to the model. “How to launch it” below gives the exact image and command.
  3. Wait for the download. The weights are fetched on the machine; tens of gigabytes take a few minutes on a data-centre connection. You pay by the second from the moment it starts.
  4. Stop it when you are done. A running machine bills even when idle. A stopped one costs nothing per hour, though its disk is usually still billed until you delete it.
How to launch it

No Q4_K_M file of LLaDA2.0-mini is catalogued here, so there is no exact command to vouch for. Start the machine from the llama.cpp server image ghcr.io/ggml-org/llama.cpp:server-cuda and point -hf at a Q4_K_M build from the publisher or a quantizer you trust — search Hugging Face for one. Check its file size against the memory figure on this page before you rent.

Every machine holds the whole model at Q4_K_M and 8,192 tokens of context, no offload. Speeds are this site’s single-stream decode estimates; prices are what each provider’s own API quoted, on-demand, for the whole machine. Vast hosts below 98% measured reliability are left out.

Referral links Vast.ai, RunPod and Novita pay us a share of what you spend if you sign up through these buttons. It costs you nothing, and it never decides an order or a recommendation: both are computed from the live price and the speed, and options that pay us nothing are listed and recommended on the same terms. How we rank

Buying a card instead, or paying by the token? Compare a year of LLaDA2.0-mini three ways →

Under the hood

Architecture, read from the publisher’s file

The numbers every figure above is computed from, with the file they came from.

Architecture

✓ Architecture read from the published config.json

Retrieved 2026-09-01 at pinned commit dad945cac317; parameter count from the safetensors index at the same revision.

Architecture
llada2_moe
Layers
20
Hidden size
2,048
Attention heads
16
KV heads
4
Head dimension
128
Feed-forward width
5,120
Vocabulary
157,184
Context ceiling
32,768
Sliding window
4,096
RoPE theta
600,000
Experts
256
Experts / token
8
Expert width
512
Shared experts
1

Where the memory goes

tokenembedding× 20 decoder blocksGrouped-query attention16 query · 4 KV headswindow 4,096Routed experts8 of 256 per tokenall residentoutputprojectiongrows with contextcapacity ≠ traffic

Grouped-query attention shares each key/value head across 4 query heads, so the KV cache is 25% of what multi-head attention would need at the same context.

Open the exact official config.json ↗

More from inclusionAI

Ling-3.0-flashLing-3.0-tinyRing-2.5-1T

Use this answer in your own product

As JSON, from the API
curl -s https://llmbottleneck.com/v1/analyze \
  -H "Authorization: Bearer $LLMB_KEY" -H "content-type: application/json" \
  -d '{"model":"inclusionai-llada2-0-mini","quantization":"Q4_K_M","context":8192,"hardware":"nvidia-geforce-rtx-4090"}'

Same engine, same evidence, every field sourced. Free key in one step →

On your page, as a widget
<script src="https://llmbottleneck.com/widget.js"
  data-model="inclusionai-llada2-0-mini" data-quantization="Q4_K_M"
  data-hardware="nvidia-geforce-rtx-4090" data-context="8192"></script>

No key needed. Unbranded, with your own buy button, on Pro and Business →

Citing this page

LLM Bottleneck. “LLaDA2.0-mini VRAM and hardware requirements.” Architecture from inclusionAI/LLaDA2.0-mini at revision dad945cac317, retrieved 2026-09-01. https://llmbottleneck.com/models/inclusionai-llada2-0-mini

Every figure above is either the published value or a reconstruction whose measured error is on the accuracy page.

llmbottleneck
catalogue 2026-10-03models 327devices 135