Specification

Release date: 11 Aug 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
Openness: open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Architecture: Qwen3_5MoeForCausalLM
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
Parameters: 1.25T
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Active parameters: 95B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
Languages: en
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
Base model: Qwen/Qwen3.8-2.4T-A95B-FP8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
File size: 1372.4 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
Hugging Face repo: amd/Qwen3.8-2.4T-A95B-Quark-MXFP4
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Pipeline tag: text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Model card: huggingface.co/amd/Qwen3.8-2.4T-A95B-Quark-MXFP4
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Downloads: 10,642
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
Likes: 5
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
Gated: No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
Last modified: 2026-08-14T04:23:23+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 59 min agomedium
Downloads all time: 11,022
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
Model type: qwen3_5_moe_text
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
Tags: transformers, safetensors, qwen3_5_moe_text, text-generation, en, 8-bit, quark
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
Weights dtype: BF16, U8
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min 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

20

Source tiers

T220

Freshest observation

55 min 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.

Languages: en
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium

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	—	718.0 GB	No
AMD Instinct MI325X	4bit	256 GB	718.0 GB	No
AMD Instinct MI300X	4bit	192 GB	718.0 GB	No
Apple M2 Ultra	4bit	—	718.0 GB	No
NVIDIA B200	4bit	180 GB	718.0 GB	No
NVIDIA H200	4bit	141 GB	718.0 GB	No
Apple M1 Ultra	4bit	—	718.0 GB	No
Apple M3 Max	4bit	—	718.0 GB	No
Apple M4 Max	4bit	—	718.0 GB	No
NVIDIA DGX Spark	4bit	128 GB	718.0 GB	No
Apple M2 Max	4bit	—	718.0 GB	No
NVIDIA A100 80GB	4bit	80 GB	718.0 GB	No
NVIDIA H100 SXM	4bit	80 GB	718.0 GB	No
Apple M1 Max	4bit	—	718.0 GB	No
Apple M4 Pro	4bit	—	718.0 GB	No
Apple M3 Pro	4bit	—	718.0 GB	No
Apple M1 Pro	4bit	—	718.0 GB	No
Apple M2 Pro	4bit	—	718.0 GB	No
Apple M4	4bit	—	718.0 GB	No
NVIDIA GeForce RTX 5090	4bit	32 GB	718.0 GB	No
Apple M2	4bit	—	718.0 GB	No
Apple M3	4bit	—	718.0 GB	No
NVIDIA GeForce RTX 3090	4bit	24 GB	718.0 GB	No
NVIDIA GeForce RTX 4090	4bit	24 GB	718.0 GB	No
Apple M1	4bit	—	718.0 GB	No

Ancestors 1

Qwen/Qwen3.8-2.4T-A95B-FP8Qwen

This model

amd/Qwen3.8-2.4T-A95B-Quark-MXFP4

1.25T params

Quantizations 0

None recorded.

Descendants 0

None recorded.

Papers 0

No papers linked yet.

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 · Downloads

1 claims · 1 propertiesShow all properties

Downloadsmetric.downloads1

Claim history for Downloads
Value	Valid from → to	Status	Source	Confidence	Extractor
10,642	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/Qwen3.8-2.4T-A95B-Quark-MXFP4AMD
New model: amd/Qwen3.8-2.4T-A95B-Quark-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/Qwen3.8-2.4T-A95B-Quark-MXFP4/raw/main/README.md	model_card	T2· Quality secondary	1 min ago	1
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/amd/Qwen3.8-2.4T-A95B-Quark-MXFP4	model_page	T2· Quality secondary	55 min 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.