Specification

Release date: 27 Feb 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 min agomedium
Openness: open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Architecture: Qwen3_5MoeForConditionalGeneration
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 min agomedium
Parameters: 19.7B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Active parameters: 10B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 min agomedium
Base model: Qwen/Qwen3.5-122B-A10B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 min agomedium
File size: 76.7 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 min agomedium
Hugging Face repo: Intel/Qwen3.5-122B-A10B-int4-AutoRound
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Model card: huggingface.co/Intel/Qwen3.5-122B-A10B-int4-AutoRound
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Downloads: 234,314
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 min agomedium
Likes: 49
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 min agomedium
Gated: No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 min agomedium
Last modified: 2026-04-16T02:23:58+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 1 h agomedium
Downloads all time: 1,493,195
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 min agomedium
Model type: qwen3_5_moe
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 min agomedium
Tags: safetensors, qwen3_5_moe, 4-bit, auto-round
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 min agomedium
Weights dtype: BF16, F16, I32
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 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

17

Source tiers

T217

Freshest observation

53 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.

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	—	11.8 GB	Yes
AMD Instinct MI325X	4bit	256 GB	11.8 GB	Yes
AMD Instinct MI300X	4bit	192 GB	11.8 GB	Yes
Apple M2 Ultra	4bit	—	11.8 GB	Yes
NVIDIA B200	4bit	180 GB	11.8 GB	Yes
NVIDIA H200	4bit	141 GB	11.8 GB	Yes
Apple M1 Ultra	4bit	—	11.8 GB	Yes
Apple M3 Max	4bit	—	11.8 GB	Yes
Apple M4 Max	4bit	—	11.8 GB	Yes
NVIDIA DGX Spark	4bit	128 GB	11.8 GB	Yes
Apple M2 Max	4bit	—	11.8 GB	Yes
NVIDIA A100 80GB	4bit	80 GB	11.8 GB	Yes
NVIDIA H100 SXM	4bit	80 GB	11.8 GB	Yes
Apple M1 Max	4bit	—	11.8 GB	Yes
Apple M4 Pro	4bit	—	11.8 GB	Yes
Apple M3 Pro	4bit	—	11.8 GB	Yes
Apple M1 Pro	4bit	—	11.8 GB	Yes
Apple M2 Pro	4bit	—	11.8 GB	Yes
Apple M4	4bit	—	11.8 GB	Yes
NVIDIA GeForce RTX 5090	4bit	32 GB	11.8 GB	Yes
Apple M2	4bit	—	11.8 GB	Yes
Apple M3	4bit	—	11.8 GB	Yes
NVIDIA GeForce RTX 3090	4bit	24 GB	11.8 GB	Yes
NVIDIA GeForce RTX 4090	4bit	24 GB	11.8 GB	Yes
Apple M1	4bit	—	11.8 GB	Yes

Ancestors 1

Qwen3.5-122B-A10BQwen

This model

Intel/Qwen3.5-122B-A10B-int4-AutoRound

19.7B params

Quantizations 0

None recorded.

Descendants 0

None recorded.

Papers 1

arXiv:2309.05516Active
35

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 · File size

1 claims · 1 propertiesShow all properties

File sizefile_size_gb1

Claim history for File size
Value	Valid from → to	Status	Source	Confidence	Extractor
76.7 GB	11 Sept 2026 21:40 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 modelModelIntel/Qwen3.5-122B-A10B-int4-AutoRoundIntel
New model: Intel/Qwen3.5-122B-A10B-int4-AutoRound (Intel)
huggingface
huggingface.co

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/Intel/Qwen3.5-122B-A10B-int4-AutoRound/raw/main/README.md	model_card	T2· Quality secondary	11 min ago	1
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/Intel/Qwen3.5-122B-A10B-int4-AutoRound	model_page	T2· Quality secondary	53 min ago	1
Hugging Face Hub (public pages, model cards, papers)	huggingface.co/models?author=Intel&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.