selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

Mistral-Large-4-1T-A52B

Side-by-side specs, memory needs, licence, runtimes and benchmarks. Add up to 4 models.

--vram
any
--gpus
--quant
--add

On your GPU

  • Mistral-Large-4-1T-A52B
Property
Overview
TaskVision
Parameters1T
Active parameters52B
Context length1M
Input → output
Released30 Sept 2026
LicenceCustom licence
Gated downloadno
Memory and speed
Fits your hardwarepick a GPU above≈602 GB
VRAM at Q4≈602 GB
VRAM at Q8≈1049 GB
VRAM at FP16≈1965 GB
Est. generation speedpick a GPU above—
Popularity
Downloads / 30 days19.3K
Likes1.7K
Runs with
Jan
KoboldCpp
llama.cpp
LM Studio
LocalAI
MLX
Ollama
Transformers
Ollama tag—
Architecture
ArchitectureMistralLarge4ForConditionalGeneration
Layers72
Attention / KV heads64 / 64
Vocabulary204 800
Weights dtypebfloat16
GGUF availableyes

Keep comparing

Memory figures are estimates for an 8K context at the chosen quantisation (Q4_K_M for LLMs by default). Speeds are rough, memory-bound estimates. Self-reported benchmark scores come from the model authors.