Skip to content

Mistral Large 2 123B VRAM Sizing Guide

Bottom line up front: Detailed memory allocation, hardware cluster requirements, and inference scaling parameters for Mistral Large 2 123B.

Dense Architecture
Total Parameters
123B
Active Weights
123B
Native Context
128k tokens
Recommended Cluster
4x H100 (80GB) or 2x H200 (141GB)

Comprehensive Memory Matrix

The table below outlines precise weight memory footprints and minimum single node hardware requirements across standard quantization tiers for Mistral Large 2 123B.

Precision TierBytes per ParamWeights Memory (GB)Min Single Node RequirementParallelism Split (TP / PP)
FP162.0 bytes246.0 GB4x H100 (80GB) or 2x H200 (141GB)Tensor Parallelism 4 (BF16) or TP 2 (FP8)
FP81.0 byte123.0 GB4x H100 (80GB) or 2x H200 (141GB)Tensor Parallelism 4 (BF16) or TP 2 (FP8)
INT40.5 bytes61.5 GBSingle / Multi-GPUTP 1 or 2

KV Cache Growth Matrix

Runtime KV cache memory consumption scaling across increasing context lengths for batch size 1 and batch size 8.

Context LengthBatch Size 1 (KV Cache)Batch Size 8 (KV Cache)
4k tokens1.38 GB11.00 GB
8k tokens2.75 GB22.00 GB
16k tokens5.50 GB44.00 GB
32k tokens11.00 GB88.00 GB
64k tokens22.00 GB176.00 GB
128k tokens44.00 GB352.00 GB

Hardware Architecture Analysis

BF16 weights require ~246 GB (fits 4x 80GB H100 or 2x 141GB H200); FP8 (~123 GB) fits comfortably across 2x 80GB GPUs or 1x H200.

Interactive Sizing Workbench

Configure custom batch sizes, quantization levels, and parallelism splits interactively below.

Free LLM VRAM Calculator

Calculate precise GPU memory requirements for inference, full fine-tuning, and LoRA training. Plan your cluster architecture accurately for Llama 3.1, DeepSeek, Qwen, and custom models across modern NVIDIA accelerators.

Model and Workload Parameters

8,192 tokens
4,09632,76865,536131,072
1
1163264

VRAM Breakdown

Model Weights246 GB
KV Cache2.75 GB
Activation Overhead0.14 GB
CUDA Runtime2 GB
Total VRAM Required250.89 GB

Denpex Developer Tools

Install the Denpex VS Code and Open VSX extension with over 2,000 active installs for real-time diagnostics. Decode offline browser logs instantly with our GPU log analyzer.

Hardware Cluster Sizing and GPU Recommendations

Estimated minimum GPU count required to host 250.89 GB VRAM safely with headroom for concurrency.

GPU AcceleratorVRAM per GPURequired CountEstimated Utilization
NVIDIA B200192 GB2 GPUs65%
NVIDIA H200141 GB2 GPUs89%
NVIDIA H10080 GB4 GPUs78%
NVIDIA A10080 GB4 GPUs78%
NVIDIA RTX PRO 6000 Blackwell96 GB3 GPUs87%
NVIDIA L40S48 GB6 GPUs87%
NVIDIA RTX 509032 GB8 GPUs98%
NVIDIA RTX 409024 GB11 GPUs95%

Diagnose OOM, KV-Cache, or NCCL Crashes on Mistral Large 2 123B

Hit an allocation crash, KV-cache startup failure, or multi-GPU collective timeout while serving or fine-tuning Mistral Large 2 123B? Isolate the failing rank or allocator bottleneck locally in seconds before renting extra nodes.

Try Denpex for 30 days. FREE.

No credit card. No automatic subscription. See whether Denpex helps with an incident you already understand.

Start your free 30-day Team evaluation

Up to 50 diagnoses a day for 30 days. Verify your work email to activate an eligible company evaluation, then replay a resolved incident and compare the evidence and next steps with your team's confirmed cause.

Use your company email, for example alex@yourcompany.com.

Who qualifies?

Company email domains activate the free 30-day Team evaluation (up to 50 diagnoses a day) after an email and domain check, whatever mail provider you use. If we cannot verify your domain automatically, support reviews it: write to support@denpex.com. Free local diagnosis in the editor extension needs no account.

Using a personal email (Gmail, Outlook, Naver, QQ) or solo cluster? Create a free $0 account (no work email required) to save 7-day history and unlock AI fallback, or send a cluster crash log for a live walkthrough.

Optimize Infrastructure Directly from VS Code

Join over 2,000 active developers using our Open VSX extension to analyze GPU logs, track cluster utilization, and streamline model deployments in real time.