LocalClaw/LLM/Mistral Small 4 (119B-A6.5B)
Open-weight MoE

Mistral Small 4 (119B-A6.5B)

Catalogue summary: Mistral AI hybrid instruct, reasoning and coding MoE. Apache 2.0, 256K context, multimodal input, official NVFP4 weights and a practical Q4_K_M GGUF for high-memory offline workstations.

Repository editorial metadata; verify comparative claims in the linked upstream material.

96 GB catalogue minimum96 GB RAMQ4_K_MCoding assistant
Choose an app

Pick the app you already use. No terminal and no command to copy.

Compare models
Open in LM StudioOpens the app on this model's download screenOpen in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloadsOpen llama.cpp setupAdvanced option: opens the model filesUse with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
119B (6.5B active, MoE)
Minimum RAM
96 GB
Model size
72.1 GB
Quantization
Q4_K_M

Can Mistral Small 4 (119B-A6.5B) run locally?

Mistral Small 4 (119B-A6.5B) has a catalogue minimum of 96 GB RAM with Q4_K_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use mistral-small-4-119b-2603 as the catalogue search term in a compatible runtime, and confirm the available format on the upstream repository before download.

Model sourcePublic GGUF repository (verified 2026-09-07): lmstudio-community/Mistral-Small-4-119B-2603-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningvisionagentpowerlong-contextmultilingual

Install path

01
Check RAM fitMinimum 96 GB RAM. Start with the Q4_K_M quant.
02
Load the modelSearch mistral-small-4-119b-2603 in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: mistral
  • Parameters: 119B (6.5B active, MoE)
  • Recommended quantization: Q4_K_M
  • Catalogue minimum RAM: 96 GB
  • Catalogue model size: 72.1 GB
  • Tags: chat, code, reasoning, vision, agent, power, long-context, multilingual

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • code
  • reasoning
  • vision
  • agent
  • power

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
3
quality
9
coding
9
reasoning
9

Technical notes

Developer
Mistral AI
License
Apache 2.0
Context window
262,144 tokens
Architecture
Granular Mixture-of-Experts model with 119B total parameters, 128 experts, four active experts and about 6.5B active parameters per token. It accepts text and images and can switch between instant and reasoning modes.

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

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

Ministral 3 14B Instruct 14BMistral Small 3.2 (24B) 24BMistral Large (123B) 123BMistral Small 3.1 (24B) 24BMinistral 3 8B Instruct 8BMistral Small (24B) 24BDevstral (24B) 24BMagistral (24B) 24B

Where to go next