Intel/Qwen3.8-Flash-Next-W4A16-AutoRound
Updated 20 min ago · first seen 11 Sept 2026
model_01M294YS470NKPRW92DN4R86MW
- Parameters
- 75.4B
- T2 · 2 h ago
- Released
- 28 Aug 2026
- T2 · 2 h ago
- License
- other
- T2 · 2 h ago
Specification
- Release date
- 28 Aug 2026
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- License
- other
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Architecture
- Qwen4ExpForConditionalGeneration
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Parameters
- 75.4B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Base model
- Qwen/Qwen3.8-Flash-Next
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- File size
- 181.2 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Hugging Face repo
- Intel/Qwen3.8-Flash-Next-W4A16-AutoRound
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Pipeline tag
- image-text-to-text
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Downloads
- 30,761
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 20 min agomedium
- Likes
- 19
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 20 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Last modified
- 2026-08-31T13:34:32+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- License name
- qwen-community-1.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 49 min agomedium
- License url
- LICENSE
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Downloads all time
- 30,761
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Model type
- qwen4_exp
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Tags
- transformers, safetensors, qwen4_exp, image-text-to-text, 4-bit, auto-round
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Weights dtype
- BF16, F16, I32, I64
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 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
21
Source tiers
T221
Freshest observation
20 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
Current prices
No current prices recorded
Price history
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.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| NVIDIA DGX B200 | 4bit | 1,440 GB | 43.8 GB | Yes |
| Apple M3 Ultra | 4bit | — | 43.8 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 43.8 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 43.8 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 43.8 GB | Yes |
| Apple M2 Ultra | 4bit | — | 43.8 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 43.8 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 43.8 GB | Yes |
| NVIDIA H200 NVL | 4bit | 141 GB | 43.8 GB | Yes |
| Apple M1 Ultra | 4bit | — | 43.8 GB | Yes |
| Apple M3 Max | 4bit | — | 43.8 GB | Yes |
| Apple M4 Max | 4bit | — | 43.8 GB | Yes |
| Mac Studio (Apple M5 Max) | 4bit | — | 43.8 GB | Yes |
| MacBook Pro (Apple M5 Max) | 4bit | — | 43.8 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 43.8 GB | Yes |
| Apple M2 Max | 4bit | — | 43.8 GB | Yes |
| NVIDIA H100 NVL | 4bit | 94 GB | 43.8 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 43.8 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 43.8 GB | Yes |
| Apple M1 Max | 4bit | — | 43.8 GB | Yes |
| Apple M4 Pro | 4bit | — | 43.8 GB | Yes |
| Mac mini (Apple M5 Pro) | 4bit | — | 43.8 GB | Yes |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 43.8 GB | Yes |
| Apple M3 Pro | 4bit | — | 43.8 GB | No |
| Apple M1 Pro | 4bit | — | 43.8 GB | No |
| Apple M2 Pro | 4bit | — | 43.8 GB | No |
| Apple M4 | 4bit | — | 43.8 GB | No |
| iMac (Apple M4) | 4bit | — | 43.8 GB | No |
| Mac mini (Apple M6) | 4bit | — | 43.8 GB | No |
| MacBook Air (Apple M5) | 4bit | — | 43.8 GB | No |
| MacBook Pro (Apple M5) | 4bit | — | 43.8 GB | No |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 43.8 GB | No |
| Apple M2 | 4bit | — | 43.8 GB | No |
| Apple M3 | 4bit | — | 43.8 GB | No |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 43.8 GB | No |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 43.8 GB | No |
| Apple M1 | 4bit | — | 43.8 GB | No |
Ancestors 1
- Qwen3.8 FlashQwen
This model
Intel/Qwen3.8-Flash-Next-W4A16-AutoRound
75.4B params
Quantizations 0
None recorded.
Descendants 0
None recorded.
Papers 1
- arXiv:2309.05516Active35
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 · License
Licenselicense1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| other | → 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 →
New model: Intel/Qwen3.8-Flash-Next-W4A16-AutoRound (Intel)
huggingface
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=Intel&p=0&sort=downloads | listing | T2· Quality secondary | 20 min ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/Intel/Qwen3.8-Flash-Next-W4A16-AutoRound/raw/main/README.md | model_card | T2· Quality secondary | 49 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/Intel/Qwen3.8-Flash-Next-W4A16-AutoRound | model_page | T2· Quality secondary | 2 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.