- Size
- 41.8B parametersfrom the GGUF metadata of a conversion, because this repo's own weights are packed: mradermacher/falcon-40b-instruct-i1-GGUF
- Licence
- unknown, Apache License 2.0Our reading, check the licence: You can use, change and redistribute the model, including commercially. Keep the licence and any notices, and say which files you changed; you do not have to publish your changes. It includes a patent licence that ends for anyone who sues over patents in the work.
- On the Hub since
- 25 May 2023the date the repo was created
- Context length
- Not known
- Kind
- Base model (no base model declared on the Hub)FalconForCausalLM
- On Hugging Face
- tiiuae/falcon-40b-instruct12k downloads in the last 30 days, 1.2k likes
Scores
- Shots: 533.8%Stanford HELM
Epoch's name: falcon-40b-instruct. Best closed model on this set: gpt-4-0314, 92.0% (OpenAI). All 170 results
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.
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: 15.0 GB, worked out from the model's config (tiiuae/falcon-40b-instruct), 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
mradermacher/falcon-40b-instruct-i1-GGUF (converted by mradermacher), 1.7k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XXS | 15.7 GBfile size | 31.2 GB15.7 + 15.0 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/falcon-40b-instruct-i1-GGUF:IQ3_XXSOllama ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:IQ3_XXSDownload hf download mradermacher/falcon-40b-instruct-i1-GGUF --include "falcon-40b-instruct.i1-IQ3_XXS.gguf" --local-dir falcon-40b-instruct-i1-GGUF |
| IQ3_XS | 17.0 GBfile size | 32.5 GB17.0 + 15.0 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/falcon-40b-instruct-i1-GGUF:IQ3_XSOllama ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:IQ3_XSDownload hf download mradermacher/falcon-40b-instruct-i1-GGUF --include "falcon-40b-instruct.i1-IQ3_XS.gguf" --local-dir falcon-40b-instruct-i1-GGUF |
| IQ3_S | 17.5 GBfile size | 33.0 GB17.5 + 15.0 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/falcon-40b-instruct-i1-GGUF:IQ3_SOllama ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:IQ3_SDownload hf download mradermacher/falcon-40b-instruct-i1-GGUF --include "falcon-40b-instruct.i1-IQ3_S.gguf" --local-dir falcon-40b-instruct-i1-GGUF |
| Q3_K_S | 17.5 GBfile size | 33.0 GB17.5 + 15.0 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/falcon-40b-instruct-i1-GGUF:Q3_K_SOllama ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:Q3_K_SDownload hf download mradermacher/falcon-40b-instruct-i1-GGUF --include "falcon-40b-instruct.i1-Q3_K_S.gguf" --local-dir falcon-40b-instruct-i1-GGUF |
| IQ3_M | 18.3 GBfile size | 33.8 GB18.3 + 15.0 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/falcon-40b-instruct-i1-GGUF:IQ3_MOllama ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:IQ3_MDownload hf download mradermacher/falcon-40b-instruct-i1-GGUF --include "falcon-40b-instruct.i1-IQ3_M.gguf" --local-dir falcon-40b-instruct-i1-GGUF |
| Q3_K_M | 19.2 GBfile size | 34.7 GB19.2 + 15.0 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/falcon-40b-instruct-i1-GGUF:Q3_K_MOllama ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:Q3_K_MDownload hf download mradermacher/falcon-40b-instruct-i1-GGUF --include "falcon-40b-instruct.i1-Q3_K_M.gguf" --local-dir falcon-40b-instruct-i1-GGUF |
| Q3_K_L | 20.6 GBfile size | 36.1 GB20.6 + 15.0 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/falcon-40b-instruct-i1-GGUF:Q3_K_LOllama ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:Q3_K_LDownload hf download mradermacher/falcon-40b-instruct-i1-GGUF --include "falcon-40b-instruct.i1-Q3_K_L.gguf" --local-dir falcon-40b-instruct-i1-GGUF |
| IQ4_XS | 21.0 GBfile size | 36.5 GB21.0 + 15.0 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/falcon-40b-instruct-i1-GGUF:IQ4_XSOllama ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:IQ4_XSDownload hf download mradermacher/falcon-40b-instruct-i1-GGUF --include "falcon-40b-instruct.i1-IQ4_XS.gguf" --local-dir falcon-40b-instruct-i1-GGUF |
| Q4_0 | 22.3 GBfile size | 37.8 GB22.3 + 15.0 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/falcon-40b-instruct-i1-GGUF:Q4_0Ollama ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:Q4_0Download hf download mradermacher/falcon-40b-instruct-i1-GGUF --include "falcon-40b-instruct.i1-Q4_0.gguf" --local-dir falcon-40b-instruct-i1-GGUF |
| Q4_K_S | 22.6 GBfile size | 38.1 GB22.6 + 15.0 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/falcon-40b-instruct-i1-GGUF:Q4_K_SOllama ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:Q4_K_SDownload hf download mradermacher/falcon-40b-instruct-i1-GGUF --include "falcon-40b-instruct.i1-Q4_K_S.gguf" --local-dir falcon-40b-instruct-i1-GGUF |
| Q4_K_M | 24.2 GBfile size | 39.7 GB24.2 + 15.0 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/falcon-40b-instruct-i1-GGUF:Q4_K_MOllama ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:Q4_K_MDownload hf download mradermacher/falcon-40b-instruct-i1-GGUF --include "falcon-40b-instruct.i1-Q4_K_M.gguf" --local-dir falcon-40b-instruct-i1-GGUF |
| Q5_K_S | 27.4 GBfile size | 42.9 GB27.4 + 15.0 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/falcon-40b-instruct-i1-GGUF:Q5_K_SOllama ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:Q5_K_SDownload hf download mradermacher/falcon-40b-instruct-i1-GGUF --include "falcon-40b-instruct.i1-Q5_K_S.gguf" --local-dir falcon-40b-instruct-i1-GGUF |
| Q5_K_M | 29.0 GBfile size | 44.5 GB29.0 + 15.0 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/falcon-40b-instruct-i1-GGUF:Q5_K_MOllama ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:Q5_K_MDownload hf download mradermacher/falcon-40b-instruct-i1-GGUF --include "falcon-40b-instruct.i1-Q5_K_M.gguf" --local-dir falcon-40b-instruct-i1-GGUF |
| Q6_K | 32.6 GBfile size | 48.1 GB32.6 + 15.0 + 0.50 | Commandsllama.cpp llama-server -hf mradermacher/falcon-40b-instruct-i1-GGUF:Q6_KOllama ollama run hf.co/mradermacher/falcon-40b-instruct-i1-GGUF:Q6_KDownload hf download mradermacher/falcon-40b-instruct-i1-GGUF --include "falcon-40b-instruct.i1-Q6_K.gguf" --local-dir falcon-40b-instruct-i1-GGUF |
The 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, 13:43 UTC. The repo. Found a mistake on this page? Tell us.