Skip to content
AI Atlas
ModelActiveIdentity probable

upstage/Llama-2-70b-instruct

Upstagefamily · Llama 2huggingface.co/upstage/Llama-2-70b-instruct

Open in Graph
data quality50

Updated 3 h ago · first seen 12 Sept 2026

model_01M2AS5MX63FHF5Z34KH3JYW91

Overview

Identity

Canonical model
Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
None recorded
API aliases
NoneIdentifiers under which providers and evaluators refer to this model.
Folded evaluation variants
0Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Openness not classified yet — no sourced evidence to place this model in the ontology.

Key facts

Release date

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium

Hugging Face repo

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 h agomedium

Capabilities

Modalities

Modalities
text
Input
text
Output
text

Capabilities

  • Tool calling

    Unavailable

  • Structured output

    Unavailable

  • Reasoning

    Unavailable

  • Vision

    Unavailable

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

No capability flags have been observed from a source yet — we do not infer them.

Languages

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium

Hardware fit37

Estimated

23 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—40.8 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—40.8 GB est.Yes
Apple M2 Ultra4bit—40.8 GB est.Yes
Apple M1 Ultra4bit—40.8 GB est.Yes
Apple M3 Max4bit—40.8 GB est.Yes
Apple M4 Max4bit—40.8 GB est.Yes
Mac Studio (Apple M5 Max)4bit—40.8 GB est.Yes
MacBook Pro (Apple M5 Max)4bit—40.8 GB est.Yes
Apple M2 Max4bit—40.8 GB est.Yes
Apple M1 Max4bit—40.8 GB est.Yes
Apple M4 Pro4bit—40.8 GB est.Yes
Mac mini (Apple M5 Pro)4bit—40.8 GB est.Yes
MacBook Pro (Apple M5 Pro)4bit—40.8 GB est.Yes
NVIDIA A100 80GB4bit80 GB40.8 GB est.Yes
NVIDIA H100 SXM4bit80 GB40.8 GB est.Yes
NVIDIA H100 NVL4bit94 GB40.8 GB est.Yes
NVIDIA DGX Spark4bit128 GB40.8 GB est.Yes
NVIDIA H2004bit141 GB40.8 GB est.Yes
NVIDIA H200 NVL4bit141 GB40.8 GB est.Yes
NVIDIA B2004bit180 GB40.8 GB est.Yes
AMD Instinct MI300X4bit192 GB40.8 GB est.Yes
AMD Instinct MI325X4bit256 GB40.8 GB est.Yes
NVIDIA DGX B2004bit1,440 GB40.8 GB est.Yes
Apple M3 Pro4bit—40.8 GB est.No
Apple M1 Pro4bit—40.8 GB est.No
Apple M2 Pro4bit—40.8 GB est.No
Apple M44bit—40.8 GB est.No
iMac (Apple M4)4bit—40.8 GB est.No
Mac mini (Apple M6)4bit—40.8 GB est.No
MacBook Air (Apple M5)4bit—40.8 GB est.No
MacBook Pro (Apple M5)4bit—40.8 GB est.No
Apple M24bit—40.8 GB est.No
Apple M34bit—40.8 GB est.No
Apple M14bit—40.8 GB est.No
NVIDIA GeForce RTX 30904bit24 GB40.8 GB est.No
NVIDIA GeForce RTX 40904bit24 GB40.8 GB est.No
NVIDIA GeForce RTX 50904bit32 GB40.8 GB est.No
Assumptions (7)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), independent of architecture (GQA/MLA models need less).
  • A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
  • Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
  • Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).
  • Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.

Versions & Artifacts0

Version history

Parametersfirst observation only

12 Sept 2026current

Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

Artifacts 0

No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.

Timeline1

Full timeline →

Change history19

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.
19 claims · 19 properties

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
24 Jul 2023 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Architecturearchitecture1

Claim history for Architecture
ValueValid from → toStatusSourceConfidenceExtractor
LlamaForCausalLM → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Parametersparameter_count1

Claim history for Parameters
ValueValid from → toStatusSourceConfidenceExtractor
70B → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Modalitiesmodalities1

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Input modalitiesmodalities_input1

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Languageslanguages1

Claim history for Languages
ValueValid from → toStatusSourceConfidenceExtractor
en → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
upstage/Llama-2-70b-instruct → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Pipeline tagpipeline_tag1

Claim history for Pipeline tag
ValueValid from → toStatusSourceConfidenceExtractor
text-generation → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model cardmodel_card_url1

Claim history for Model card
ValueValid from → toStatusSourceConfidenceExtractor
https://huggingface.co/upstage/Llama-2-70b-instruct → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloadsmetric.downloads1

Claim history for Downloads
ValueValid from → toStatusSourceConfidenceExtractor
333 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Likesmetric.likes1

Claim history for Likes
ValueValid from → toStatusSourceConfidenceExtractor
64 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Accessaccess1

Claim history for Access
ValueValid from → toStatusSourceConfidenceExtractor
open → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Last modifiedlast_modified1

Claim history for Last modified
ValueValid from → toStatusSourceConfidenceExtractor
2023-08-03T22:01:09+00:00 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Library namelibrary_name1

Claim history for Library name
ValueValid from → toStatusSourceConfidenceExtractor
transformers → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloads all timemetric.downloads_all_time1

Claim history for Downloads all time
ValueValid from → toStatusSourceConfidenceExtractor
65,406 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model typemodel_type1

Claim history for Model type
ValueValid from → toStatusSourceConfidenceExtractor
llama → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Tagstags1

Claim history for Tags
ValueValid from → toStatusSourceConfidenceExtractor
en, instruct, instruction, llama, llama-2, pytorch, text-generation, transformers, upstage → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Weights availableweights_available1

Claim history for Weights available
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

19

Source tiers

T219

Freshest observation

3 h ago

Conflicts

None

Source documents 2

Source documents
SourceDocumentTypeTierLast observedSnapshots
Hugging Face Hub (public pages, model cards, papers)huggingface.co/upstage/Llama-2-70b-instruct model_pageT2· Quality secondary3 h ago1
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=upstage&p=0&sort=downloads listingT2· Quality secondary4 h ago2

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (50/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →