Mistral Large 4

Running Mistral Large 4 locally

At Q4_K_M and 4K of context, Mistral Large 4 needs about 663.8 GB — 603.1 GB of weights, 0.32 GB of KV cache and a 60.3 GB activation buffer. No card in this index clears that comfortably at Q4_K_M, so at that level it is a multi-GPU or CPU-offload proposition. Its smaller IQ2_XXS build needs about 311.5 GB, which the Mac M5 Ultra 512G clears comfortably. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.

What longer context costs

Going from 4K to 32K adds about 2.24 GB, taking the total to 666.2 GB. That is gentler than the parameter count suggests: only 63 of 72 layers keep a KV cache that grows with context, so the cache scales at a fraction of the usual rate. The model's native window is 1M; holding all of it at Q4_K_M would need about 754 GB.

Which build to download

This index only tracks Mistral Large 4 in GGUF, across 4 levels (IQ2_XXS, Q2_K, Q4_K_M, Q8_0). No per-level perplexity sweep has been published for this model, so the quality column is empty rather than estimated — within one model, more bits per weight is the only ordering the data supports. No throughput has been measured for this model on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 — CUDA only, and now archived, so local use rather than serving.

Common questions

How much VRAM does Mistral Large 4 need?

About 663.8 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 666.2 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.

Can Mistral Large 4 run on a single GPU?

Not comfortably on any single card in this index at Q4_K_M. It needs about 663.8 GB, which means splitting across GPUs or offloading layers to system RAM. Its smaller IQ2_XXS build needs about 311.5 GB, which the Mac M5 Ultra 512G clears comfortably.

Which quantization of Mistral Large 4 should I use?

No published quality comparison exists for this model, so pick by footprint: IQ2_XXS is the largest level here that fits a single machine in this index, and a higher bits-per-weight level is more faithful. All 4 levels in the index are IQ2_XXS, Q2_K, Q4_K_M, Q8_0. Note this is a mixture-of-experts model — all parameters must be resident even though only a fraction are active per token, so the memory cost follows the total, not the active count.