- Size
- 33.1B parameterscounted from the safetensors header on the Hub
- 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
- 24 Oct 2026the date the repo was created
- Context length
- 512k tokensfrom the model's config
- Fine-tune
- of Nanbeige/Nanbeige4.3-33B-BaseLlamaForCausalLM
- On Hugging Face
- Nanbeige/Nanbeige4.3-33B24k downloads in the last 30 days, 1.1k 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: 1.6 GB, worked out from the model's config (Nanbeige/Nanbeige4.3-33B), 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
bartowski/Nanbeige_Nanbeige4.3-33B-GGUF (converted by bartowski), 165k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| IQ3_XXS | 13.5 GBfile size | 15.6 GB13.5 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ3_XXSOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ3_XXSDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-IQ3_XXS.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| Q3_K_S | 14.2 GBfile size | 16.3 GB14.2 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q3_K_SOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q3_K_SDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q3_K_S.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| IQ3_XS | 14.2 GBfile size | 16.3 GB14.2 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ3_XSOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ3_XSDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-IQ3_XS.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| Q3_K_M | 14.8 GBfile size | 17.0 GB14.8 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q3_K_MOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q3_K_MDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q3_K_M.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| Q3_K_L | 16.1 GBfile size | 18.2 GB16.1 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q3_K_LOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q3_K_LDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q3_K_L.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| IQ3_M | 16.6 GBfile size | 18.7 GB16.6 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ3_MOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ3_MDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-IQ3_M.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| IQ4_XS | 17.4 GBfile size | 19.5 GB17.4 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ4_XSOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ4_XSDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-IQ4_XS.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| Q4_0 | 18.0 GBfile size | 20.1 GB18.0 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_0Ollama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_0Download hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q4_0.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| Q4_K_S | 18.4 GBfile size | 20.5 GB18.4 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_SOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_SDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q4_K_S.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| Q4_K_M | 19.4 GBfile size | 21.5 GB19.4 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_MOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_MDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q4_K_M.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| IQ4_NL | 19.4 GBfile size | 21.6 GB19.4 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ4_NLOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ4_NLDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-IQ4_NL.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| Q4_1 | 19.7 GBfile size | 21.9 GB19.7 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_1Ollama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_1Download hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q4_1.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| Q4_K_L | 20.8 GBfile size | 22.9 GB20.8 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_LOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_LDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q4_K_L.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| Q5_K_S | 22.0 GBfile size | 24.2 GB22.0 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q5_K_SOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q5_K_SDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q5_K_S.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| Q5_K_M | 23.4 GBfile size | 25.5 GB23.4 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q5_K_MOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q5_K_MDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q5_K_M.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| Q6_K_S | 25.8 GBfile size | 28.0 GB25.8 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q6_K_SOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q6_K_SDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q6_K_S.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| Q6_K | 27.0 GBfile size | 29.1 GB27.0 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q6_KOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q6_KDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q6_K.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| Q6_K_L | 28.3 GBfile size | 30.4 GB28.3 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q6_K_LOllama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q6_K_LDownload hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q6_K_L.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| Q8_0 | 32.8 GBfile size | 34.9 GB32.8 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q8_0Ollama ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q8_0Download hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q8_0.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
| BF16 | 61.7 GBfile size, 2 parts | 63.8 GB61.7 + 1.6 + 0.50 | Commandsllama.cpp llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:BF16Download hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-bf16/Nanbeige_Nanbeige4.3-33B-bf16-*-of-00002.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitNurymanau/Nanbeige4.3-33B-MLX-4bit | 17.4 GBfile size | 19.5 GB17.4 + 1.6 + 0.50 | Download page |
| MLX 4bitpratikgx/Nanbeige4.3-33B-MLX-4bit | 17.4 GBfile size | 19.5 GB17.4 + 1.6 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| BF16original weights | 61.7 GBfile size | 63.8 GB61.7 + 1.6 + 0.50 |
hf download Nanbeige/Nanbeige4.3-33B --local-dir Nanbeige4.3-33BOther conversions (23; sizes not read)
- Nanbeige/Nanbeige4.3-33B-INT4 Other, int4, by the maker, 978 downloads
- Nanbeige/Nanbeige4.3-33B-FP8 FP8, by the maker, 896 downloads
- Nanbeige/Nanbeige4.3-33B-INT8 Other, int8, by the maker, 300 downloads
- axteam/Nanbeige4.3-33B-NVFP4 NVFP4, 1.9k downloads
- axteam/Nanbeige4.3-33B-NVFP4A16 NVFP4, 1.9k downloads
- primitive-ai/Nanbeige4.3-33B-NVFP4 NVFP4, 1.6k downloads
- webbrain-one/Nanbeige4.3-33B-NVFP4 NVFP4, 1.6k downloads
- primitive-ai/Nanbeige4.3-33B-FP8 FP8, 884 downloads
- infosave/Nanbeige4.3-33B-cmf Other, 646 downloads
- Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound GPTQ, w4a16, 497 downloads
- cyankiwi/Nanbeige4.3-33B-AWQ-INT4 AWQ, int4, 387 downloads
- acrogenesis/Nanbeige4.3-33B-EXL3-3.55bpw EXL3, 383 downloads
- lxe/Nanbeige4.3-33B-EXL3-2.5bpw EXL3, 357 downloads
- ProCreations/Nanbeige4.3-33B-FP8 FP8, 309 downloads
- yamz-labs/Nanbeige4.3-33B-EXL3-Yamz EXL3, 300 downloads
- vcruz305/Nanbeige4.3-33B-SAGE-EXL3-4.50bpw EXL3, 294 downloads
- jeonghyeon00/Nanbeige4.3-33B-W4A16-AutoRound Other, w4a16, 293 downloads
- axteam/Nanbeige4.3-33B-AWQ-4bit AWQ, 4bit, 235 downloads
- jeonghyeon00/Nanbeige4.3-33B-w4a16-gptq-compressed-tensors GPTQ, w4a16, 215 downloads
- axteam/Nanbeige4.3-33B-FP8-dynamic FP8, 199 downloads
- evanrodgers/Nanbeige4.3-33B-W4A16-G128 GPTQ, w4a16, 186 downloads
- axteam/Nanbeige4.3-33B-AWQ-8bit AWQ, 8bit, 182 downloads
- heliophage/Nanbeige4.3-33B-W4A16-GPTQ GPTQ, w4a16, 89 downloads
The Hub tags 100 or more 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.