Model
Llama 4 Scout 17B 16E Instruct
Recorded as suitable for chat, rag, multilingual, vision, long context.
- Source
- Model registry API
- Verified
- 19 Sep 2026
- Confidence
- High
01What this is
- Author
- meta-llama
- Family
- Llama 4
- Task
- vision-language
- Hugging Face
- meta-llama/Llama-4-Scout-17B-16E-Instruct
- OpenRouter
- meta-llama/llama-4-scout
- Also known as
- Llama 4 Scout, llama-4-scout, llama4 scout
02Registry facts
- LicenceFACT
other
- FreshRetrieved 19 Sep 2026
- ParametersFACT
108.6B
- FreshRetrieved 19 Sep 2026
- Context lengthFACT
not returned by the registry
- Evidence not verified
- Downloads (30 days)FACT
161,489
- FreshRetrieved 19 Sep 2026
- LikesFACT
1,350
- FreshRetrieved 19 Sep 2026
- GatedFACT
yes
- FreshRetrieved 19 Sep 2026
Model
- downloadsFACT
161489
- Verification may be outdatedRetrieved 19 Sep 2026
- gatedFACT
true
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · GoogleFACT
1310720
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · NovitaFACT
131072
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · DeepInfraFACT
327680
- Verification may be outdatedRetrieved 19 Sep 2026
- likesFACT
1350
- Verification may be outdatedRetrieved 19 Sep 2026
- model licenseFACT
other
- Verification may be outdatedRetrieved 19 Sep 2026
- parameter countFACT
108641793536
- Verification may be outdatedRetrieved 19 Sep 2026
Pricing
- hosted price completion per m · GoogleFACT
0.7000
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · NovitaFACT
0.5900
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · DeepInfraFACT
0.3000
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · GoogleFACT
0.2500
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · NovitaFACT
0.1800
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · DeepInfraFACT
0.1000
- AgeingRetrieved 19 Sep 2026
Other
- available on platform · awsFACT
aws
Evidence not verified — the quoted phrase was not found in the fetched document.
- Evidence not verified
- last modifiedFACT
2025-05-22T23:44:50.000Z
- Verification may be outdatedRetrieved 19 Sep 2026
- libraryFACT
transformers
- AgeingRetrieved 19 Sep 2026
03VRAM by quantisation
Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: 108.6B parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).
| Quantisation | Weights | Total |
|---|---|---|
| bf16bf16 is two bytes per weight, the same arithmetic as fp16. | 217.28 GB | 267.16 GB |
| int8 | 108.64 GB | 142.23 GB |
| int4 | 54.32 GB | 79.76 GB |
What this estimate assumes
- Weights: 108.6B parameters × 2 bytes per parameter (fp16) = 217.28 GB.
- No model configuration was supplied, so the KV cache uses the size heuristic for this band: 0.459 MB per token, from extrapolated above 90B — no configuration was fetched for this band.
- KV cache: 0.459 MB per token × 8,192 tokens of context × 4 concurrent requests = 15.03 GB, sized for every user holding a full context at once.
- Overhead: 15% of weights plus KV cache for the runtime, activations and memory fragmentation = 34.85 GB.
- GB means 10⁹ bytes, matching how GPU memory is advertised.
- KV cache held at fp16 (2 bytes per element); quantising weights does not by itself quantise the cache.
- Peak figure, not average: prefix caching and paged attention usually keep real usage lower, while speculative decoding, CUDA graphs and a second resident model push it higher.
- "Concurrent" counts requests generated at the same instant, not people: 4 simultaneous requests is the worst case this estimate is built on — measure yours before buying.
04Hardware profiles
No hardware profile was sized for this answer.
05Hosted providers
- Prompt (per million tokens, USD)FACT
0.09999999999999999
Source: openrouter
- FreshRetrieved 19 Sep 2026
- Completion (per million tokens, USD)FACT
0.3
- FreshRetrieved 19 Sep 2026
| Provider | Context |
|---|---|
| DeepInfra | 327,680 |
| Novita | 131,072 |
| 1,310,720 |
06Deployment stacks
No published deployment stack names this model yet.
07Evidence
- 01–09Tier 4official repository / model cardOpenRouter
OpenRouter endpoints — meta-llama/llama-4-scout
https://openrouter.ai/api/v1/models/meta-llama/llama-4-scout/endpoints
AgeingRetrieved 19 Sep 2026sha256:16e128da95199 records · · · · · · · ·
- 10–16Tier 4official repository / model cardHugging Face Hub
Hugging Face model card data — meta-llama/Llama-4-Scout-17B-16E-Instruct
https://huggingface.co/api/models/meta-llama/Llama-4-Scout-17B-16E-Instruct
Verification may be outdatedRetrieved 19 Sep 2026sha256:46eba700074b7 records · · · · · ·
Improve this page
Sign in to contribute
From the field
0 deployments · 0 questions
Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.