- Size
- 176B parameterscounted from the safetensors header on the Hub
- Licence
- unknown, BigScience BLOOM RAIL 1.0Our reading, check the licence: A responsible AI licence: commercial use is allowed, but the licence lists uses that are not allowed, and you must pass those use restrictions on to anyone you give the model or a changed version to.
- On the Hub since
- 19 May 2022the date the repo was created
- Context length
- Not known
- Kind
- Base model (no base model declared on the Hub)BloomForCausalLM
- On Hugging Face
- bigscience/bloom7.3k downloads in the last 30 days, 5.1k likes
Scores
- Shots: 570.4%Stanford HELM
Epoch's name: bloom. Best closed model on this set: Inflection-1, 89.7% (Inflection AI). All 136 results
- Shots: 59.5%Stanford HELM
Epoch's name: bloom. Best closed model on this set: gpt-4-0314, 92.0% (OpenAI). All 170 results
- Shots: 074.4%Stanford HELM
Epoch's name: bloom. Best closed model on this set: gpt-4-0314, 95.3% (OpenAI). All 113 results
Claimed by the maker Claimed
- humaneval pass@10.15542682926829265
- humaneval pass@100.3278356276947017
- humaneval pass@1000.5719815685597749
Values as the card gives them, unscaled. Source: the model card on the Hugging Face Hub. Claimed scores are never mixed with independent ones.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 4.0 GB, a rough allowance by model size, because we do not have this model's attention config. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
DevQuasar-13/bigscience.bloom-GGUF (converted by DevQuasar-13), 441 downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K | 63.5 GBfile size, 5 parts | 68.0 GB63.5 + 4.0 + 0.50 | Commandsllama.cpp llama-server -hf DevQuasar-13/bigscience.bloom-GGUF:Q2_KDownload hf download DevQuasar-13/bigscience.bloom-GGUF --include "bigscience.bloom.Q2_K-*-of-00005.gguf" --local-dir bigscience.bloom-GGUF |
| Q3_K_M | 88.0 GBfile size, 7 parts | 92.5 GB88.0 + 4.0 + 0.50 | Commandsllama.cpp llama-server -hf DevQuasar-13/bigscience.bloom-GGUF:Q3_K_MDownload hf download DevQuasar-13/bigscience.bloom-GGUF --include "bigscience.bloom.Q3_K_M-*-of-00007.gguf" --local-dir bigscience.bloom-GGUF |
| Q4_K_M | 106.9 GBfile size, 9 parts | 111.4 GB106.9 + 4.0 + 0.50 | Commandsllama.cpp llama-server -hf DevQuasar-13/bigscience.bloom-GGUF:Q4_K_MDownload hf download DevQuasar-13/bigscience.bloom-GGUF --include "bigscience.bloom.Q4_K_M-*-of-00009.gguf" --local-dir bigscience.bloom-GGUF |
| Q5_K_M | 124.4 GBfile size, 10 parts | 128.9 GB124.4 + 4.0 + 0.50 | Commandsllama.cpp llama-server -hf DevQuasar-13/bigscience.bloom-GGUF:Q5_K_MDownload hf download DevQuasar-13/bigscience.bloom-GGUF --include "bigscience.bloom.Q5_K_M-*-of-00010.gguf" --local-dir bigscience.bloom-GGUF |
| Q6_K | 137.4 GBfile size, 11 parts | 141.9 GB137.4 + 4.0 + 0.50 | Commandsllama.cpp llama-server -hf DevQuasar-13/bigscience.bloom-GGUF:Q6_KDownload hf download DevQuasar-13/bigscience.bloom-GGUF --include "bigscience.bloom.Q6_K-*-of-00011.gguf" --local-dir bigscience.bloom-GGUF |
| Q8_0 | 178.0 GBfile size, 14 parts | 182.5 GB178.0 + 4.0 + 0.50 | Commandsllama.cpp llama-server -hf DevQuasar-13/bigscience.bloom-GGUF:Q8_0Download hf download DevQuasar-13/bigscience.bloom-GGUF --include "bigscience.bloom.Q8_0-*-of-00014.gguf" --local-dir bigscience.bloom-GGUF |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 328.3 GBfile size | 332.8 GB328.3 + 4.0 + 0.50 |
hf download bigscience/bloom --local-dir bloomThe Hub tags 2 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
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, 13:57 UTC. The repo. Found a mistake on this page? Tell us.