Updated 1 h ago · first seen 12 Sept 2026
model_01M29X246HKG8FSKPQMDRFS7AY
- Parameters
- 20B
- T2 · 9 h ago
- Released
- 4 Aug 2025
- T2 · 9 h ago
Specification
- Family
- Qwen
Source:Qwen — official blogT2observed 9 h agomediumLLM-extracted
- Release date
- 4 Aug 2025
Source:Qwen — official blogT2observed 9 h agomediumLLM-extracted
- Status
- announced
Source:Qwen — official blogT2observed 9 h agomediumLLM-extracted
- Openness
- proprietary
Source:Qwen — official blogT2observed 9 h agomediumLLM-extracted
- Architecture
- MMDiT
Source:Qwen — official blogT2observed 9 h agomediumLLM-extracted
- Parameters
- 20B
Source:Qwen — official blogT2observed 9 h agomediumLLM-extracted
- Mixture of experts
- No
Source:Qwen — official blogT2observed 9 h agomediumLLM-extracted
- Modalities
- image, text
Source:Qwen — official blogT2observed 9 h agomediumLLM-extracted
- Input modalities
- image, text
Source:Qwen — official blogT2observed 9 h agomediumLLM-extracted
- Output modalities
- image
Source:Qwen — official blogT2observed 9 h agomediumLLM-extracted
- Languages
- Chinese, English
Source:Qwen — official blogT2observed 9 h agomediumLLM-extracted
- Official page
- qwen.ai
Source:Qwen — official blogT2observed 9 h agomediumLLM-extracted
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
15
Source tiers
T215
Freshest observation
9 h ago
Conflicts
None
Modalities
- Modalities
- imagetext
- Input
- imagetext
- Output
- image
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
Yes
Qwen — official blog · T2
Audio
No
Qwen — official blog · T2
Fine-tuning available
Unavailable
- Languages
- Chinese, English
Source:Qwen — official blogT2observed 9 h agomediumLLM-extracted
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 | 12.0 GB | Yes |
| Apple M3 Ultra | 4bit | — | 12.0 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 12.0 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 12.0 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 12.0 GB | Yes |
| Apple M2 Ultra | 4bit | — | 12.0 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 12.0 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 12.0 GB | Yes |
| NVIDIA H200 NVL | 4bit | 141 GB | 12.0 GB | Yes |
| Apple M1 Ultra | 4bit | — | 12.0 GB | Yes |
| Apple M3 Max | 4bit | — | 12.0 GB | Yes |
| Apple M4 Max | 4bit | — | 12.0 GB | Yes |
| Mac Studio (Apple M5 Max) | 4bit | — | 12.0 GB | Yes |
| MacBook Pro (Apple M5 Max) | 4bit | — | 12.0 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 12.0 GB | Yes |
| Apple M2 Max | 4bit | — | 12.0 GB | Yes |
| NVIDIA H100 NVL | 4bit | 94 GB | 12.0 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 12.0 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 12.0 GB | Yes |
| Apple M1 Max | 4bit | — | 12.0 GB | Yes |
| Apple M4 Pro | 4bit | — | 12.0 GB | Yes |
| Mac mini (Apple M5 Pro) | 4bit | — | 12.0 GB | Yes |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 12.0 GB | Yes |
| Apple M3 Pro | 4bit | — | 12.0 GB | Yes |
| Apple M1 Pro | 4bit | — | 12.0 GB | Yes |
| Apple M2 Pro | 4bit | — | 12.0 GB | Yes |
| Apple M4 | 4bit | — | 12.0 GB | Yes |
| iMac (Apple M4) | 4bit | — | 12.0 GB | Yes |
| Mac mini (Apple M6) | 4bit | — | 12.0 GB | Yes |
| MacBook Air (Apple M5) | 4bit | — | 12.0 GB | Yes |
| MacBook Pro (Apple M5) | 4bit | — | 12.0 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 12.0 GB | Yes |
| Apple M2 | 4bit | — | 12.0 GB | Yes |
| Apple M3 | 4bit | — | 12.0 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 12.0 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 12.0 GB | Yes |
| Apple M1 | 4bit | — | 12.0 GB | Yes |
Ancestors 0
None recorded.
This model
Qwen-Image
20B params
Quantizations 0
None recorded.
Descendants 1
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
Familyfamily1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Qwen | → current | current | Qwen — official blogT2 | medium | llm |
Release daterelease_date1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 4 Aug 2025 | → current | current | Qwen — official blogT2 | medium | llm |
Statusstatus1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| announced | → current | current | Qwen — official blogT2 | medium | llm |
Opennessopenness1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| proprietary | → current | current | Qwen — official blogT2 | medium | llm |
Architecturearchitecture1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| MMDiT | → current | current | Qwen — official blogT2 | medium | llm |
Parametersparameter_count1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 20B | → current | current | Qwen — official blogT2 | medium | llm |
Mixture of expertsis_moe1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| No | → current | current | Qwen — official blogT2 | medium | llm |
Modalitiesmodalities1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| image, text | → current | current | Qwen — official blogT2 | medium | llm |
Input modalitiesmodalities_input1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| image, text | → current | current | Qwen — official blogT2 | medium | llm |
Output modalitiesmodalities_output1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| image | → current | current | Qwen — official blogT2 | medium | llm |
Languageslanguages1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Chinese, English | → current | current | Qwen — official blogT2 | medium | llm |
Official pageofficial_url1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| qwen.ai | → current | current | Qwen — official blogT2 | medium | llm |
Audioaudio1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| No | → current | current | Qwen — official blogT2 | medium | llm |
Training data notestraining_data_notes1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Enhanced multi-task training paradigm. | → current | current | Qwen — official blogT2 | medium | llm |
Visionvision1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Yes | → current | current | Qwen — official blogT2 | medium | llm |
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 →
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Qwen — official blog | qwenlm.github.io/blog/qwen-image | news | T1· Official | 9 h ago | 1 |
| Qwen — official blog | qwenlm.github.io/blog/qwen-image-edit | news | T1· Official | 9 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.