tiny-aya-global
Coheredocs.cohere.com/docs/models
Tiny Aya Global is a 3.35B instruction-tuned multilingual model with the best balance across languages and regions. Supports 70 languages.
Updated 4 min ago · first seen 11 Sept 2026
model_01M294H9A6MD8XR7FS8WAHSK2R
- Parameters
- 3.35B
- T1 · 11 min ago
- Context
- 8K tokens
- T1 · 11 min ago
Specification
- Family
- Aya
Source:Cohere — docs & blogT1observed 11 min agohigh
- Status
- active
Source:Cohere — docs & blogT1observed 11 min agohigh
- Openness
- restricted
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 min agomedium
- Parameters
- 3.35B
Source:Cohere — docs & blogT1observed 11 min agohigh
- Context window
- 8K tokens
Source:Cohere — docs & blogT1observed 11 min agohigh
- Max output
- 8K tokens
Source:Cohere — docs & blogT1observed 11 min agohigh
- Modalities
- text
Source:Cohere — docs & blogT1observed 11 min agohigh
- Input modalities
- text
Source:Cohere — docs & blogT1observed 11 min agohigh
- API model id
- tiny-aya-global
Source:Cohere — docs & blogT1observed 11 min agohigh
- Hugging Face repo
- CohereLabs/tiny-aya-global
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 min agomedium
- Pipeline tag
- text-generation
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 min agomedium
- Official page
Source:Cohere — docs & blogT1observed 11 min agohigh
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 min agomedium
- Downloads
- 6,966
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 min agomedium
- Likes
- 172
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 min agomedium
- Endpoints
- Chat
Source:Cohere — docs & blogT1observed 11 min agohigh
- Last modified
- 2026-07-07T14:58:13+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 4 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
19
Source tiers
T1T212 / 7
Freshest observation
4 min ago
Conflicts
1 flagged
Modalities
- Modalities
- text
- Input
- text
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
No
Cohere — docs & blog · T1
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 8K tokens
Source:Cohere — docs & blogT1observed 11 min agohigh
- Max output
- 8K tokens
Source:Cohere — docs & blogT1observed 11 min agohigh
No benchmark results recorded
Current prices
No current prices recorded
Available through 1
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 |
|---|---|---|---|---|
| Apple M3 Ultra | 4bit | — | 2.4 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 2.4 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 2.4 GB | Yes |
| Apple M2 Ultra | 4bit | — | 2.4 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 2.4 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 2.4 GB | Yes |
| Apple M1 Ultra | 4bit | — | 2.4 GB | Yes |
| Apple M3 Max | 4bit | — | 2.4 GB | Yes |
| Apple M4 Max | 4bit | — | 2.4 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 2.4 GB | Yes |
| Apple M2 Max | 4bit | — | 2.4 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 2.4 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 2.4 GB | Yes |
| Apple M1 Max | 4bit | — | 2.4 GB | Yes |
| Apple M4 Pro | 4bit | — | 2.4 GB | Yes |
| Apple M3 Pro | 4bit | — | 2.4 GB | Yes |
| Apple M1 Pro | 4bit | — | 2.4 GB | Yes |
| Apple M2 Pro | 4bit | — | 2.4 GB | Yes |
| Apple M4 | 4bit | — | 2.4 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 2.4 GB | Yes |
| Apple M2 | 4bit | — | 2.4 GB | Yes |
| Apple M3 | 4bit | — | 2.4 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 2.4 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 2.4 GB | Yes |
| Apple M1 | 4bit | — | 2.4 GB | Yes |
No lineage 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
Familyfamily1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Aya | → current | current | Cohere — docs & blogT1 | high | deterministic |
Statusstatus1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| active | → current | current | Cohere — docs & blogT1 | high | deterministic |
Opennessopenness1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| restricted | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Parametersparameter_count3conflicting claims
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 3.35B | → current | conflicting | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
| 3.35B | → current | conflicting | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
| 3.35B | → current | current | Cohere — docs & blogT1 | conflicted | deterministic |
Context windowcontext_length1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 8K tokens | → current | current | Cohere — docs & blogT1 | high | deterministic |
Max outputmax_output_tokens1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 8K tokens | → current | current | Cohere — docs & blogT1 | high | deterministic |
Modalitiesmodalities1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| text | → current | current | Cohere — docs & blogT1 | high | deterministic |
Input modalitiesmodalities_input1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| text | → current | current | Cohere — docs & blogT1 | high | deterministic |
API model idapi_model_id1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| tiny-aya-global | → current | current | Cohere — docs & blogT1 | high | deterministic |
Hugging Face repohf_repo1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| CohereLabs/tiny-aya-global | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Pipeline tagpipeline_tag1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| text-generation | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Official pageofficial_url1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://docs.cohere.com/docs/models | → current | current | Cohere — docs & blogT1 | high | deterministic |
Model cardmodel_card_url1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://huggingface.co/CohereLabs/tiny-aya-global | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Downloadsmetric.downloads1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 6,966 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Likesmetric.likes1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 172 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Descriptiondescription1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Tiny Aya Global is a 3.35B instruction-tuned multilingual model with the best balance across languages and regions. Supports 70 languages. | → current | current | Cohere — docs & blogT1 | high | deterministic |
Endpointsendpoints1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Chat | → current | current | Cohere — docs & blogT1 | high | deterministic |
Last modifiedlast_modified1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 2026-07-07T14:58:13+00:00 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Visionvision1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| No | → current | current | Cohere — docs & blogT1 | high | 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 →
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Cohere — docs & blog | docs.cohere.com/docs/models.md | model_docs | T1· Official | 11 min ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=CohereLabs&p=0&sort=downloads | listing | T2· Quality secondary | 4 min ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.