Skip to content
AI Atlas
ModelActive

nvidia/GLM-5.2-NVFP4

NVIDIAhuggingface.co/nvidia/GLM-5.2-NVFP4

Open in Graph
data quality53

Updated 6 h ago · first seen 11 Sept 2026

model_01M294ZPFTHN6YDAKKXZ01P4ZT

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 11 h agomedium

Model card
huggingface.co/nvidia/GLM-5.2-NVFP4

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 11 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Hugging Face repo

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 12 h agomedium

Hardware fit37

Estimated

4 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—219.6 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—219.6 GB est.Yes
AMD Instinct MI325X4bit256 GB219.6 GB est.Yes
NVIDIA DGX B2004bit1,440 GB219.6 GB est.Yes
Apple M2 Ultra4bit—219.6 GB est.No
Apple M1 Ultra4bit—219.6 GB est.No
Apple M3 Max4bit—219.6 GB est.No
Apple M4 Max4bit—219.6 GB est.No
Mac Studio (Apple M5 Max)4bit—219.6 GB est.No
MacBook Pro (Apple M5 Max)4bit—219.6 GB est.No
Apple M2 Max4bit—219.6 GB est.No
Apple M1 Max4bit—219.6 GB est.No
Apple M4 Pro4bit—219.6 GB est.No
Mac mini (Apple M5 Pro)4bit—219.6 GB est.No
MacBook Pro (Apple M5 Pro)4bit—219.6 GB est.No
Apple M3 Pro4bit—219.6 GB est.No
Apple M1 Pro4bit—219.6 GB est.No
Apple M2 Pro4bit—219.6 GB est.No
Apple M44bit—219.6 GB est.No
iMac (Apple M4)4bit—219.6 GB est.No
Mac mini (Apple M6)4bit—219.6 GB est.No
MacBook Air (Apple M5)4bit—219.6 GB est.No
MacBook Pro (Apple M5)4bit—219.6 GB est.No
Apple M24bit—219.6 GB est.No
Apple M34bit—219.6 GB est.No
Apple M14bit—219.6 GB est.No
NVIDIA GeForce RTX 30904bit24 GB219.6 GB est.No
NVIDIA GeForce RTX 40904bit24 GB219.6 GB est.No
NVIDIA GeForce RTX 50904bit32 GB219.6 GB est.No
NVIDIA A100 80GB4bit80 GB219.6 GB est.No
NVIDIA H100 SXM4bit80 GB219.6 GB est.No
NVIDIA H100 NVL4bit94 GB219.6 GB est.No
NVIDIA DGX Spark4bit128 GB219.6 GB est.No
NVIDIA H2004bit141 GB219.6 GB est.No
NVIDIA H200 NVL4bit141 GB219.6 GB est.No
NVIDIA B2004bit180 GB219.6 GB est.No
AMD Instinct MI300X4bit192 GB219.6 GB est.No
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).

Lineage

Open in Graph →
Explicit derived_from / fine_tuned_from / distilled_from relations stated by sources; artifacts collapsed by kind.
ANCESTORS 1Z.ai GLM 5.2753.3BZ.ai GLM 5.2 — 753.3Bnvidia/GLM-5.2-NVFP4381B params · this modelnvidia/GLM-5.2-NVFP4 — 381B params · this model

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
22 Jun 2026 → 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
mit → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Architecturearchitecture1

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

Parametersparameter_count1

Claim history for Parameters
ValueValid from → toStatusSourceConfidenceExtractor
381B → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Base modelbase_model1

Claim history for Base model
ValueValid from → toStatusSourceConfidenceExtractor
zai-org/GLM-5.2 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

File sizefile_size_gb1

Claim history for File size
ValueValid from → toStatusSourceConfidenceExtractor
464.9 GB → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
nvidia/GLM-5.2-NVFP4 → 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/nvidia/GLM-5.2-NVFP4 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloadsmetric.downloads1

Claim history for Downloads
ValueValid from → toStatusSourceConfidenceExtractor
893,641 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Likesmetric.likes1

Claim history for Likes
ValueValid from → toStatusSourceConfidenceExtractor
323 → 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
2026-08-31T15:59:10+00:00 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Library namelibrary_name1

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

Downloads all timemetric.downloads_all_time1

Claim history for Downloads all time
ValueValid from → toStatusSourceConfidenceExtractor
3,442,330 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model typemodel_type1

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

Tagstags1

Claim history for Tags
ValueValid from → toStatusSourceConfidenceExtractor
Model Optimizer, safetensors, glm_moe_dsa, nvidia, ModelOpt, GLM-5, quantized, 4-bit precision, FP4, fp4, text-generation, 8-bit, modelopt → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Weights dtypeweights_dtype1

Claim history for Weights dtype
ValueValid from → toStatusSourceConfidenceExtractor
BF16, F32, U8 → 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

6 h ago

Conflicts

None

Source documents 3

Source documents
SourceDocumentTypeTierLast observedSnapshots
Hugging Face Hub (public pages, model cards, papers)huggingface.co/nvidia/GLM-5.2-NVFP4/raw/main/README.md model_cardT2· Quality secondary5 h ago1
Hugging Face Hub (public pages, model cards, papers)huggingface.co/nvidia/GLM-5.2-NVFP4 model_pageT2· Quality secondary6 h ago4
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=nvidia&p=0&sort=downloads listingT2· Quality secondary6 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 →