Skip to content
Weights Not Walls
Menu

Nanbeige

Nanbeige4.3-33B

Reviewed
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

file sizes read from the Hub 19 Nov 2026

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.

FormatSizeMemory neededGet it
IQ3_XXS13.5 GBfile size15.6 GB13.5 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ3_XXS
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ3_XXS
Download
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_S14.2 GBfile size16.3 GB14.2 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q3_K_S
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q3_K_S
Download
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_XS14.2 GBfile size16.3 GB14.2 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ3_XS
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ3_XS
Download
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_M14.8 GBfile size17.0 GB14.8 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q3_K_M
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q3_K_M
Download
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_L16.1 GBfile size18.2 GB16.1 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q3_K_L
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q3_K_L
Download
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_M16.6 GBfile size18.7 GB16.6 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ3_M
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ3_M
Download
hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-IQ3_M.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF
IQ4_XS17.4 GBfile size19.5 GB17.4 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ4_XS
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ4_XS
Download
hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-IQ4_XS.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF
Q4_018.0 GBfile size20.1 GB18.0 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_0
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_0
Download
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_S18.4 GBfile size20.5 GB18.4 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_S
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_S
Download
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_M19.4 GBfile size21.5 GB19.4 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_M
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_M
Download
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_NL19.4 GBfile size21.6 GB19.4 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ4_NL
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:IQ4_NL
Download
hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-IQ4_NL.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF
Q4_119.7 GBfile size21.9 GB19.7 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_1
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_1
Download
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_L20.8 GBfile size22.9 GB20.8 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_L
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_L
Download
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_S22.0 GBfile size24.2 GB22.0 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q5_K_S
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q5_K_S
Download
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_M23.4 GBfile size25.5 GB23.4 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q5_K_M
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q5_K_M
Download
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_S25.8 GBfile size28.0 GB25.8 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q6_K_S
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q6_K_S
Download
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_K27.0 GBfile size29.1 GB27.0 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q6_K
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q6_K
Download
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_L28.3 GBfile size30.4 GB28.3 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q6_K_L
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q6_K_L
Download
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_032.8 GBfile size34.9 GB32.8 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q8_0
Ollama
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q8_0
Download
hf download bartowski/Nanbeige_Nanbeige4.3-33B-GGUF --include "Nanbeige_Nanbeige4.3-33B-Q8_0.gguf" --local-dir Nanbeige_Nanbeige4.3-33B-GGUF
BF1661.7 GBfile size, 2 parts63.8 GB61.7 + 1.6 + 0.50
Commands
llama.cpp
llama-server -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:BF16
Download
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

FormatSizeMemory neededRepo
MLX 4bitNurymanau/Nanbeige4.3-33B-MLX-4bit17.4 GBfile size19.5 GB17.4 + 1.6 + 0.50Download page
MLX 4bitpratikgx/Nanbeige4.3-33B-MLX-4bit17.4 GBfile size19.5 GB17.4 + 1.6 + 0.50Download page

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
BF16original weights61.7 GBfile size63.8 GB61.7 + 1.6 + 0.50
hf download Nanbeige/Nanbeige4.3-33B --local-dir Nanbeige4.3-33B
Other conversions (23; sizes not read)

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

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

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.