What GPU do I need to run Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16?

753.3B parameters, published in BF16. View on Hugging Face

753.3B
Parameters
BF16
Native precision
GlmMoeDsaForCausalLM
Architecture
text-generation
Pipeline

GLM-5.3-F.U-AnthraClaud-Edition-BF16 is published by Blackfrost-Research on Hugging Face, with 1,001 downloads and 57 likes to date. It's a GlmMoeDsaForCausalLM model built for text-generation, published natively in BF16.

VRAM required & cheapest live GPU fit

Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
BF161403.2 GB1683.8 GBNo capable live offer found––
FP8 (quantized)701.6 GB841.9 GBNo capable live offer found––
INT4 (quantized)350.8 GB421.0 GBRTX PRO 60005$7.01/hr

A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.

INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.

GLM-5.3-F.U-AnthraClaud-Edition-BF16: KV cache by context length

The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.

Multi-head latent attention: every layer caches one compressed latent per token. Cached per token: 89,856 bytes at 16-bit.

ContextKV cache, one sequence
4K0.34 GB
32K2.7 GB
128K11.0 GB
1M (model maximum)87.8 GB

Computed from the layer, head and window counts in the model's own configuration (Blackfrost-Research/GLM-5.3-F.U-AnthraClaud-Edition-BF16), at 16 bits per cached value. Each concurrent sequence needs its own cache, on top of the weights.

GLM-5.3-F.U-AnthraClaud-Edition-BF16: common questions

Can GLM-5.3-F.U-AnthraClaud-Edition-BF16 run on a single GPU?

Not on a desktop card. At BF16 it needs 1683.8 GB of VRAM, more than a single 32 GB desktop card holds. No card currently listed on the marketplace both supports BF16 and has enough VRAM for it, so how many it would take is not something this page can answer today.

Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.

More GLM-5 models

All 23 GLM-5 models: VRAM and GPU requirements

Lineage

Based on GLM-5.3-BF16.

Alternatives at this size

Other models for text-generation within about a third of GLM-5.3-F.U-AnthraClaud-Edition-BF16's 753.3B parameters, from other model lines.

More on GLM-5.3-F.U-AnthraClaud-Edition-BF16

Related reading: H100 pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, Best GPU for LLM inference, and What AI model fine-tuning is.

Related on Aquanode: All LLaVA models and their GPU requirements, GPU requirements for GLM-5.3-Flash-UNCENSORED-FP8, and GPU requirements for GLM-5.3-Flash-Uncensored-FP8.

Your own GPU cloud accounts

One console for the GPU clouds you already rent from. Your keys stay on your machine.

$20 a month, flat

Connect your accounts

One console for the GPU clouds you already use.

Connect your accounts for $20 a month, flat. Your provider bills the GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.