Skip to content
AI Atlas
ModelActive

internlm2-20b

InternLM (Shanghai AI Laboratory)huggingface.co/internlm/internlm2-20b

Open in Graph
data quality53

Updated 7 h ago · first seen 11 Sept 2026

model_01M294YW2A44EN1WV3FBYG04NF

Overview

Identity

Identity block not returned by the API for this entity.

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 13 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium

Hugging Face repo

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 13 h agomedium

Hardware fit37

Estimated

37 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—12.0 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—12.0 GB est.Yes
Apple M2 Ultra4bit—12.0 GB est.Yes
Apple M1 Ultra4bit—12.0 GB est.Yes
Apple M3 Max4bit—12.0 GB est.Yes
Apple M4 Max4bit—12.0 GB est.Yes
Mac Studio (Apple M5 Max)4bit—12.0 GB est.Yes
MacBook Pro (Apple M5 Max)4bit—12.0 GB est.Yes
Apple M2 Max4bit—12.0 GB est.Yes
Apple M1 Max4bit—12.0 GB est.Yes
Apple M4 Pro4bit—12.0 GB est.Yes
Mac mini (Apple M5 Pro)4bit—12.0 GB est.Yes
MacBook Pro (Apple M5 Pro)4bit—12.0 GB est.Yes
Apple M3 Pro4bit—12.0 GB est.Yes
Apple M1 Pro4bit—12.0 GB est.Yes
Apple M2 Pro4bit—12.0 GB est.Yes
Apple M44bit—12.0 GB est.Yes
iMac (Apple M4)4bit—12.0 GB est.Yes
Mac mini (Apple M6)4bit—12.0 GB est.Yes
MacBook Air (Apple M5)4bit—12.0 GB est.Yes
MacBook Pro (Apple M5)4bit—12.0 GB est.Yes
Apple M24bit—12.0 GB est.Yes
Apple M34bit—12.0 GB est.Yes
Apple M14bit—12.0 GB est.Yes
NVIDIA GeForce RTX 30904bit24 GB12.0 GB est.Yes
NVIDIA GeForce RTX 40904bit24 GB12.0 GB est.Yes
NVIDIA GeForce RTX 50904bit32 GB12.0 GB est.Yes
NVIDIA A100 80GB4bit80 GB12.0 GB est.Yes
NVIDIA H100 SXM4bit80 GB12.0 GB est.Yes
NVIDIA H100 NVL4bit94 GB12.0 GB est.Yes
NVIDIA DGX Spark4bit128 GB12.0 GB est.Yes
NVIDIA H2004bit141 GB12.0 GB est.Yes
NVIDIA H200 NVL4bit141 GB12.0 GB est.Yes
NVIDIA B2004bit180 GB12.0 GB est.Yes
AMD Instinct MI300X4bit192 GB12.0 GB est.Yes
AMD Instinct MI325X4bit256 GB12.0 GB est.Yes
NVIDIA DGX B2004bit1,440 GB12.0 GB est.Yes
Assumptions (6)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead.
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache approximated at 0.5 GB per 8 192 tokens of context, 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).

Papers1

Timeline1

Full timeline →
  • New modelModelinternlm2-20bInternLM (Shanghai AI Laboratory)

    New model: internlm2-20b (InternLM (Shanghai AI Laboratory))

    huggingface
    huggingface.co

Change history16

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

Viewing AI Atlas as of 1 Jan 2025 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

internlm2-20b was not yet in AI Atlas on 1 Jan 2025

First seen 11 Sept 2026. Nothing is inferred backwards: no attribute is shown for dates before the first observation.
16 claims · 16 properties

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
12 Jan 2024 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Opennessopenness1

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

Licenselicense1

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

Architecturearchitecture1

Claim history for Architecture
ValueValid from → toStatusSourceConfidenceExtractor
InternLM2ForCausalLM → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Parametersparameter_count1

Claim history for Parameters
ValueValid from → toStatusSourceConfidenceExtractor
20B → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
internlm/internlm2-20b → 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/internlm/internlm2-20b → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloadsmetric.downloads1

Claim history for Downloads
ValueValid from → toStatusSourceConfidenceExtractor
19,663 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Likesmetric.likes1

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

Gatedgated1

Claim history for Gated
ValueValid from → toStatusSourceConfidenceExtractor
No → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Last modifiedlast_modified1

Claim history for Last modified
ValueValid from → toStatusSourceConfidenceExtractor
2025-03-13T07:04:49+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
646,891 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model typemodel_type1

Claim history for Model type
ValueValid from → toStatusSourceConfidenceExtractor
internlm2 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Tagstags1

Claim history for Tags
ValueValid from → toStatusSourceConfidenceExtractor
transformers, pytorch, internlm2, text-generation, custom_code → 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

16

Source tiers

T216

Freshest observation

7 h ago

Conflicts

None

Source documents 3

Source documents
SourceDocumentTypeTierLast observedSnapshots
Hugging Face Hub (public pages, model cards, papers)huggingface.co/internlm/internlm2-20b/raw/main/README.md model_cardT2· Quality secondary7 h ago1
Hugging Face Hub (public pages, model cards, papers)huggingface.co/internlm/internlm2-20b model_pageT2· Quality secondary7 h ago4
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=internlm&p=0&sort=downloads listingT2· Quality secondary8 h ago6

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

Data quality (53/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →