ArtifactquantizationFP8Open weightsof Ling 3.0 Flash

inclusionAI/Ling-3.0-flash-fp4

published by inclusionAIhuggingface.co/inclusionAI/Ling-3.0-flash-fp4

This is a quantization of Ling 3.0 Flash, not an independent model. Parameters, benchmarks, prices and lineage are recorded on the canonical model. Open Ling 3.0 Flash →

data quality39

Updated 1 h ago · first seen 12 Sept 2026

artifact_01M2AS5HMZNCDHQP8TFZ4GJBY0

File size
Format
Downloads
Published

Artifact facts

Quantization format: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Weights dtype: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
File size: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Downloads: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Likes: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Hugging Face repo: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Pipeline tag: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Access: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
License: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Release date: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Last modified: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Model card: huggingface.co/inclusionAI/Ling-3.0-flash-fp4
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Tags: Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium

Hardware fit (this packaging)

Estimated

23 of 37 device × quantization combinations fit.

Run locally: your machine →

Estimated hardware fit
Hardware	Quantization	Device memory	Est. memory	Fits
Apple M3 Ultra	4bit	—	38.2 GB est.	Yes
Mac Studio (Apple M5 Ultra)	4bit	—	38.2 GB est.	Yes
Apple M2 Ultra	4bit	—	38.2 GB est.	Yes
Apple M1 Ultra	4bit	—	38.2 GB est.	Yes
Apple M3 Max	4bit	—	38.2 GB est.	Yes
Apple M4 Max	4bit	—	38.2 GB est.	Yes
Mac Studio (Apple M5 Max)	4bit	—	38.2 GB est.	Yes
MacBook Pro (Apple M5 Max)	4bit	—	38.2 GB est.	Yes
Apple M2 Max	4bit	—	38.2 GB est.	Yes
Apple M1 Max	4bit	—	38.2 GB est.	Yes
Apple M4 Pro	4bit	—	38.2 GB est.	Yes
Mac mini (Apple M5 Pro)	4bit	—	38.2 GB est.	Yes
MacBook Pro (Apple M5 Pro)	4bit	—	38.2 GB est.	Yes
NVIDIA A100 80GB	4bit	80 GB	38.2 GB est.	Yes
NVIDIA H100 SXM	4bit	80 GB	38.2 GB est.	Yes
NVIDIA H100 NVL	4bit	94 GB	38.2 GB est.	Yes
NVIDIA DGX Spark	4bit	128 GB	38.2 GB est.	Yes
NVIDIA H200	4bit	141 GB	38.2 GB est.	Yes
NVIDIA H200 NVL	4bit	141 GB	38.2 GB est.	Yes
NVIDIA B200	4bit	180 GB	38.2 GB est.	Yes
AMD Instinct MI300X	4bit	192 GB	38.2 GB est.	Yes
AMD Instinct MI325X	4bit	256 GB	38.2 GB est.	Yes
NVIDIA DGX B200	4bit	1,440 GB	38.2 GB est.	Yes
Apple M3 Pro	4bit	—	38.2 GB est.	No
Apple M1 Pro	4bit	—	38.2 GB est.	No
Apple M2 Pro	4bit	—	38.2 GB est.	No
Apple M4	4bit	—	38.2 GB est.	No
iMac (Apple M4)	4bit	—	38.2 GB est.	No
Mac mini (Apple M6)	4bit	—	38.2 GB est.	No
MacBook Air (Apple M5)	4bit	—	38.2 GB est.	No
MacBook Pro (Apple M5)	4bit	—	38.2 GB est.	No
Apple M2	4bit	—	38.2 GB est.	No
Apple M3	4bit	—	38.2 GB est.	No
Apple M1	4bit	—	38.2 GB est.	No
NVIDIA GeForce RTX 3090	4bit	24 GB	38.2 GB est.	No
NVIDIA GeForce RTX 4090	4bit	24 GB	38.2 GB est.	No
NVIDIA GeForce RTX 5090	4bit	32 GB	38.2 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.

Timeline

12 Sept 2026
New artifactArtifactinclusionAI/Ling-3.0-flash-fp4inclusionAI
New artifact: inclusionAI/Ling-3.0-flash-fp4 (inclusionAI)
huggingface
huggingface.co

Full timeline →

Provenance

Attributed facts

Source tiers

T226

Freshest observation

2 h ago

Conflicts

None

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/inclusionAI/Ling-3.0-flash-fp4/raw/main/README.md	model_card	T2· Quality secondary	1 h ago	1
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/inclusionAI/Ling-3.0-flash-fp4	model_page	T2· Quality secondary	2 h ago	1
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/models?author=inclusionAI&p=0&sort=downloads	listing	T2· Quality secondary	2 h ago	2

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