Specification

Release date: 27 Jul 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Openness: restricted
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
License: apache-2.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Architecture: Qwen3VLMoeForConditionalGeneration
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Parameters: 118.8B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Active parameters: 22B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
File size: 127.4 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Hugging Face repo: amd/Qwen3-VL-235B-A22B-Instruct-MXFP4
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Pipeline tag: image-text-to-text
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Model card: huggingface.co/amd/Qwen3-VL-235B-A22B-Instruct-MXFP4
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Downloads: 23,284
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Likes: 0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Gated: auto
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Last modified: 2026-07-27T15:05:45+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Library name: transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Downloads all time: 40,119
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Model type: qwen3_vl_moe
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Tags: transformers, safetensors, qwen3_vl_moe, image-text-to-text, 8-bit, quark
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Weights dtype: BF16, F8_E4M3, U8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

19

Source tiers

T219

Freshest observation

1 h ago

Conflicts

None

Modalities

Modalities unavailable.

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.

No structured attributes yet.

No benchmark results recorded

Results appear when a tier 1–3 source publishes them; we never copy scores without a source.

Current prices

No current prices recorded

Prices appear when a provider publishes a public pricing page we crawl.

Price history

Estimated

Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.

Estimated hardware fit
Hardware	Quantization	Memory	Est. need	Fits
Apple M3 Ultra	4bit	—	68.8 GB	Yes
AMD Instinct MI325X	4bit	256 GB	68.8 GB	Yes
AMD Instinct MI300X	4bit	192 GB	68.8 GB	Yes
Apple M2 Ultra	4bit	—	68.8 GB	Yes
NVIDIA B200	4bit	180 GB	68.8 GB	Yes
NVIDIA H200	4bit	141 GB	68.8 GB	Yes
Apple M1 Ultra	4bit	—	68.8 GB	Yes
Apple M3 Max	4bit	—	68.8 GB	Yes
Apple M4 Max	4bit	—	68.8 GB	Yes
NVIDIA DGX Spark	4bit	128 GB	68.8 GB	Yes
Apple M2 Max	4bit	—	68.8 GB	Yes
NVIDIA A100 80GB	4bit	80 GB	68.8 GB	Yes
NVIDIA H100 SXM	4bit	80 GB	68.8 GB	Yes
Apple M1 Max	4bit	—	68.8 GB	No
Apple M4 Pro	4bit	—	68.8 GB	No
Apple M3 Pro	4bit	—	68.8 GB	No
Apple M1 Pro	4bit	—	68.8 GB	No
Apple M2 Pro	4bit	—	68.8 GB	No
Apple M4	4bit	—	68.8 GB	No
NVIDIA GeForce RTX 5090	4bit	32 GB	68.8 GB	No
Apple M2	4bit	—	68.8 GB	No
Apple M3	4bit	—	68.8 GB	No
NVIDIA GeForce RTX 3090	4bit	24 GB	68.8 GB	No
NVIDIA GeForce RTX 4090	4bit	24 GB	68.8 GB	No
Apple M1	4bit	—	68.8 GB	No

No lineage recorded

Lineage comes from explicit `derived_from`, `fine_tuned_from`, `distilled_from` and `quantized_from` relations stated by sources.

Papers 4

Repositories 0

No repositories linked yet.

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Pipeline tag

1 claims · 1 propertiesShow all properties

Pipeline tagpipeline_tag1

Claim history for Pipeline tag
Value	Valid from → to	Status	Source	Confidence	Extractor
image-text-to-text	11 Sept 2026 21:10 UTC → current	current	Hugging Face Hub (public pages, model cards, papers)T2	medium	deterministic

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 →

11 Sept 2026
New modelModelamd/Qwen3-VL-235B-A22B-Instruct-MXFP4AMD
New model: amd/Qwen3-VL-235B-A22B-Instruct-MXFP4 (AMD)
huggingface
huggingface.co

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/amd/Qwen3-VL-235B-A22B-Instruct-MXFP4	model_page	T2· Quality secondary	1 h ago	2
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/models?author=amd&p=0&sort=downloads	listing	T2· Quality secondary	1 h ago	2

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