- Size
- 3.3B parameterscounted from the safetensors header on the Hub
- Licence
- unknown, Creative Commons Attribution-NonCommercial 4.0Our reading, check the licence: You can use, change and share the model with credit, but not for commercial purposes.
- On the Hub since
- 13 Feb 2026the date the repo was created
- Context length
- Not known
- Fine-tune
- of CohereLabs/tiny-aya-baseCohere2ForCausalLM
- On Hugging Face
- CohereLabs/tiny-aya-global32k downloads in the last 30 days, 211 likes
Scores
No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.35 GB, worked out from the model's config (mlx-community/tiny-aya-global-8bit-mlx), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
CohereLabs/tiny-aya-global-GGUF (the maker's own conversion), 6.3k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q4_0 | 1.9 GBfile size | 2.7 GB1.9 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf CohereLabs/tiny-aya-global-GGUF:Q4_0Ollama ollama run hf.co/CohereLabs/tiny-aya-global-GGUF:Q4_0Download hf download CohereLabs/tiny-aya-global-GGUF --include "tiny-aya-global-q4_0.gguf" --local-dir tiny-aya-global-GGUF |
| Q4_K_M | 2.0 GBfile size | 2.8 GB2.0 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf CohereLabs/tiny-aya-global-GGUF:Q4_K_MOllama ollama run hf.co/CohereLabs/tiny-aya-global-GGUF:Q4_K_MDownload hf download CohereLabs/tiny-aya-global-GGUF --include "tiny-aya-global-q4_k_m.gguf" --local-dir tiny-aya-global-GGUF |
| Q8_0 | 3.3 GBfile size | 4.2 GB3.3 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf CohereLabs/tiny-aya-global-GGUF:Q8_0Ollama ollama run hf.co/CohereLabs/tiny-aya-global-GGUF:Q8_0Download hf download CohereLabs/tiny-aya-global-GGUF --include "tiny-aya-global-q8_0.gguf" --local-dir tiny-aya-global-GGUF |
| BF16 | 6.2 GBfile size | 7.1 GB6.2 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf CohereLabs/tiny-aya-global-GGUF:BF16Ollama ollama run hf.co/CohereLabs/tiny-aya-global-GGUF:BF16Download hf download CohereLabs/tiny-aya-global-GGUF --include "tiny-aya-global-bf16.gguf" --local-dir tiny-aya-global-GGUF |
| F16 | 6.2 GBfile size | 7.1 GB6.2 + 0.35 + 0.50 | Commandsllama.cpp llama-server -hf CohereLabs/tiny-aya-global-GGUF:F16Ollama ollama run hf.co/CohereLabs/tiny-aya-global-GGUF:F16Download hf download CohereLabs/tiny-aya-global-GGUF --include "tiny-aya-global-f16.gguf" --local-dir tiny-aya-global-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitSiarhei/tiny-aya-global-4bit | 1.8 GBfile size | 2.6 GB1.8 + 0.35 + 0.50 | Download page |
| MLX 8bitmlx-community/tiny-aya-global-8bit-mlx | 3.3 GBfile size | 4.2 GB3.3 + 0.35 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 6.2 GBfile size | 7.1 GB6.2 + 0.35 + 0.50 |
hf download CohereLabs/tiny-aya-global --local-dir tiny-aya-globalOther conversions (1; sizes not read)
- onnx-community/tiny-aya-global-ONNX Other, 78 downloads
The Hub tags 31 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
1 provider serves this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.
| Provider | In | Out | Context | Precision | Tokens/s | First token | Uptime 24h | Tools | JSON |
|---|---|---|---|---|---|---|---|---|---|
| coherethe maker | ? | ? | ? | not given | 131 | 0.3 s | ? | no | no |
Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.
curl https://router.huggingface.co/v1/chat/completions \
-H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \
-d '{"model": "CohereLabs/tiny-aya-global:cohere", "messages": [{"role": "user", "content": "Hello"}]}'Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.