LocalClaw/LLM/Mistral Large (123B)
Open-weight local LLM

Mistral Large (123B)

Mistral flagship. 128K context. Top-tier coding and multilingual. 262K downloads. Requires serious hardware.

Large-memory workstation 96 GB RAM Q4_K_M Enterprise AI
Run with LocalClaw Compare all models
Parameters
123B
Minimum RAM
96 GB
Model size
70 GB
Quantization
Q4_K_M

Can Mistral Large (123B) run locally?

Mistral Large (123B) needs a serious workstation with large unified memory or high VRAM.

Search for mistral-large-instruct in LM Studio or another GGUF-compatible runtime.

lmstudio-community/Mistral-Large-Instruct-2411-GGUF
chatcodequality

Install path

01
Check RAM fitMinimum 96 GB RAM. Start with the Q4_K_M quant.
02
Load the modelSearch mistral-large-instruct in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Strengths

  • Mistral flagship
  • 128K context
  • Top-tier coding and multilingual
  • 262K downloads

Limitations

  • Requires 96GB+ RAM
  • Research license — commercial restrictions
  • Very slow inference

Best use cases

  • Enterprise AI
  • Complex coding
  • Research
  • Multilingual tasks

Capability profile

speed
1
quality
10
coding
9
reasoning
10

Technical notes

Developer
Mistral AI
License
Mistral Research License
Context window
131,072 tokens
Architecture
Transformer decoder-only, 128K context

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Large unified memoryMac Studio M4 Max 128GB128GB AI PC classNVIDIA GB10 / DGX SparkHigh-memory picks128GB RAM guide

Similar models to compare

Llama 3.3 (70B) 70BQwen 2.5 (72B) 72BCommand A (111B) 111B

Where to go next