Macaron V1 Preview 744B Merged — Hardware Requirements & GPU Compatibility
ChatFunctions
Macaron V1 Preview 744B Merged is a 753.9B-parameter open language model from mindlab-research. It supports a context window of up to 202,752 tokens. At BF16 it needs about 1511.95 GB of VRAM — see which GPUs and Macs can run it below.
Macaron V1 Preview 744B Merged runs on a GPU cluster
BF16 needs ~1.5 TB · about 3 nodes of 8× H100 SXM 80 GB
MIT
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Macaron V1 Preview 744B Merged
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve mindlab-research/Macaron-V1-Preview-744B-Merged --max-model-len 16384 --tensor-parallel-size 8 --pipeline-parallel-size <nodes>Size the nodes from the table above
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Rent 3× 8-GPU H100 SXM nodes · BF16
- Estimated hourly price
- ~$64.56/hr
- est., whole cluster
- GPUs
- 24 GPUs
- 1.9 TB of VRAM
How Much VRAM Does Macaron V1 Preview 744B Merged Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 1512.0 GB | 1511 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Runs on 3 nodes of 8× H100 SXM |
Selected BF16
Brain floating point 161509.5GBat 16K context
- Weights
- 1507.7 GB
- KV cache
- 1.5 GB
- Overhead
- 0.3 GB
Server-class: ~1.5 TB at 16K context · about 3 nodes of 8× H100 SXM 80 GB
Which Hardware Can Run Macaron V1 Preview 744B Merged?
BF16 · 1512.0 GBMacaron V1 Preview 744B Merged (BF16) requires 1512.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1966+ GB is recommended. Using the full 203K context window can add up to 14.3 GB, bringing total usage to 1526.2 GB. No consumer GPU has enough memory.
Needs server-class hardware
Macaron V1 Preview 744B Merged runs on a GPU cluster · BF16 needs ~1.5 TB
| Hardware | Quant | Memory | Context | Hardware page | |
|---|---|---|---|---|---|
| GPU cluster · 3 nodes of 8× H100 SXM 80 GB | BF16 | 1509.5 GB | 32K ctx | H100 SXM → | BF16 · 1509.5 GB · 32K ctx |
By VRAM tier · typical GPUs and Macs at BF16
Consumer GPUs (up to 32 GB) and Macs up to 512 GB: too small for this model (needs ≥ 1.5 TB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
Similar models
2| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| GLM 5.3Z.ai | 130.1 | 453.8 GB | —needs > 24 GB | same size |
| DeepSeek V4.1 FlashDeepSeek | 129.5 | 458.4 GB | —needs > 24 GB | same size |
Specifications
- Publisher
- mindlab-research
- Parameters
- 753.9B
- Active parameters
- 42.4B per token
- Architecture
- GlmMoeDsaForCausalLM
- Context Length
- 202,752 tokens
- Vocabulary Size
- 154,880
- Release Date
- 2026-06-05
- License
- MIT
Frequently Asked Questions
How much VRAM does Macaron V1 Preview 744B Merged need?
Macaron V1 Preview 744B Merged requires 1512.0 GB of VRAM at BF16. Full 203K context adds up to 14.3 GB (1526.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 753.9B × 16 bits ÷ 8 = 1507.7 GB
KV Cache + Overhead ≈ 4.3 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 18.5 GB (at full 203K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Macaron V1 Preview 744B Merged?
No — Macaron V1 Preview 744B Merged requires at least 1512.0 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
Can I run Macaron V1 Preview 744B Merged on a Mac?
Macaron V1 Preview 744B Merged requires at least 1512.0 GB at BF16. None of the 146 Macs we list has that much usable memory (the largest has 508.5 GB after macOS overhead).
Can I run Macaron V1 Preview 744B Merged locally?
Yes — Macaron V1 Preview 744B Merged can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
What's the download size of Macaron V1 Preview 744B Merged?
At BF16, the download is about 1507.73 GB.
Which GPUs can run Macaron V1 Preview 744B Merged?
No single consumer GPU has enough VRAM to run Macaron V1 Preview 744B Merged at BF16 (1512.0 GB). Multi-GPU or professional hardware is required.
Which devices can run Macaron V1 Preview 744B Merged?
Macaron V1 Preview 744B Merged requires at least 1512.0 GB at BF16, which exceeds the usable memory of every unified-memory device we list (the largest has 508.5 GB).