LocalClaw/LLM/Llama 4 Scout (17B/109B MoE)
Gated model card reference

Llama 4 Scout (17B/109B MoE)

Catalogue summary: Meta Llama 4 Scout — natively multimodal MoE with 16 experts. 10M-token context window. Outperforms Gemma 3 and Mistral Small on most benchmarks at similar active cost. Llama 4 Community License.

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

Gated model cardNo public GGUF verified109B (17B active, 16 experts)2025-04
Choose an app

Only verified options can be opened. Unsupported apps are clearly marked.

Compare models
LM StudioNot available for this model
UnslothNot available for this model
OllamaNot available for this model
Open on Hugging FaceModel card, licence and access details
llama.cppNot available for this model
Use with LocalClawOptional workspace after the model is installed
Source status
Gated model card
Public GGUF
Not verified
Parameters
109B (17B active, 16 experts)
Access
Approval required

Verified source status

LocalClaw verified a gated model card for Llama 4 Scout (17B/109B MoE) on 2026-09-07. Access approval or licence acceptance is required, and no public GGUF install path is claimed.

The model card is gated and may require account approval or licence acceptance. No public GGUF file was verified, so LocalClaw does not publish an LM Studio or one-click installation path.

Gated model card (access terms apply; no public GGUF verified 2026-09-07): meta-llama/Llama-4-Scout-17B-16E-Instruct
chatvisionreasoningmultimodalpower

Access and source status

01
Open the model cardUse the verified upstream card as the source of truth for this record.
02
Request accessAccount approval or licence acceptance may be required before the files can be inspected.
03
Confirm a supported runtimeChoose a local runtime only after verifying the exact artefact, licence and hardware requirements upstream.

Catalogue record

  • Family: llama
  • Parameters: 109B (17B active, 16 experts)
  • Recommended quantization: Q4_K_M
  • Catalogue minimum RAM: 96 GB
  • Catalogue model size: 65 GB
  • Tags: chat, vision, reasoning, multimodal, power

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
  • vision
  • reasoning
  • multimodal
  • power

Capability profile

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

speed
5
quality
9
coding
8
reasoning
9

Technical notes

Developer
See upstream repository
License
See upstream repository
Context window
See upstream repository
Architecture
See upstream repository

Related catalogue entries

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

Llama 4 Scout (17B/16E MoE) 17B active (109B total, 16 experts)Llama 3.1 (70B) 70BLlama 3.3 (70B) 70BLlama 3.2 Vision (90B) 90BLlama 3.2 Vision (11B) 11BLlama 3 (8B) 8BLlama 3.1 (8B) 8BLlama 3.3 (8B) 8B

Where to go next