whatmodel.sh / Nanbeige4.3-33B
Nanbeige4.3-33B
↗ share
+ contribute
Nanbeige4.3-33B is an open-weights language model from Nanbeige, released October 2026. Its published size is 33.1B parameters and a 524k-token context window. Licence: apache-2.0.
Catalogue identity notes
Flagship 'teacher' model of the Nanbeige4.3 series (card), post-trained from Nanbeige/Nanbeige4.3-33B-Base (card base_model). HF repo created 2026-10-24 (weights uploaded 2026-10-24; pinned README commit df919e1 on 2026-10-28). Text only; thinking on by default (enable_thinking), reported evals use preserve_thinking=true. Contact address on the card is [email protected]. Licence: apache-2.0 in the card's YAML metadata; the repo has no LICENSE file. No official API and no official Ollama library entry (ollama.com/library/nanbeige and /nanbeige4.3 returned 404 on 2026-11-12). Official card documents Transformers, SGLang and vLLM (tensor parallel 4) with a local MODEL_PATH placeholder, so those are not listed as copy-pasteable routes. Benchmark comparison columns are Nanbeige re-runs of other models and are not used.
Model information sources
Release date ↗ · Weights licence ↗ · Parameter count ↗
33,118,977,024 BF16 parameters in the repo's safetensors metadata (pinned sha df919e1, observed 2026-11-12); dense LlamaForCausalLM per pinned config.json (52 layers, hidden 7168). The card names it 33B.
$ how it compares
Scored LLMs released closest to Nanbeige4.3-33B, out of 1206 with a score, then more from Nanbeige.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 3 | 84±1 | api $4.00/M | |||
| 6 | 83±1 | api $2.00/M | |||
| 10 | 81±1 | Muse Code only | |||
| 19 | 78±1 | api price unknown | |||
| 20 | 78±1 | api $8.00/M | |||
| more from Nanbeige | |||||
| 474 | 54±3 | local | |||
$ what it's good at
agent tasksnot ranked on this task yet · 5 tests
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Terminal-Bench 2.1 lab | 80.9% ✎ | ▁·▁·▁▁▄▃▅█▆█ beats 47/68 | — |
| SWE-bench Pro (split unspecified) lab | 60.3% ✎ | ▁·▁▁▁▁▁▄█▁▁▁ beats 46/64 | — |
| Terminal-Bench 4.0 lab | 23.8% ✎ | ▂·▁··▂▄▄▅█▇▄ beats 16/41 | — |
| τ³-bench lab | 48.8% ✎ | ▁▁▂▁·▁▁·▃▁▂█ beats 10/26 | — |
| Toolathlon-Verified lab | 70.4% ✎ | ▂·▂▂▅▃···▃██ beats 9/19 | — |
codingnot ranked on this task yet · 2 tests
| test | result | vs the others in its run | counts |
|---|---|---|---|
| SWE-bench Pro (split unspecified) lab | 60.3% ✎ | ▁·▁▁▁▁▁▄█▁▁▁ beats 46/64 | — |
| SciCode (level unspecified) lab | 52.6% ✎ | ▁····▃▃▄▄█▆▃ beats 41/42 | — |
mathnot ranked on this task yet · 1 test
other tests4 not in a task · 0.0% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| GPQA Diamond lab | 89.5% ✎ | ▁▁▁▁▂▃▅▆▇▇█▂ beats 276/336 | — |
| NL2Repo lab | 53.0% ✎ | ▂▂▂·▃▃▅█▃▃▆▃ beats 17/24 | — |
| AutomationBench v1.0.6 lab | 54.2% ✎ | ▂···▂·▂▂··█▆ beats 8/10 | — |
| DeepPlanning lab | 63.3% ✎ | ▂···▂··▄█▄·▃ beats 10/10 | — |
$ where to run it
Memory is what a version takes in GPU memory (or a Mac's unified memory) with an 8k-token conversation. With less, it runs partly from system RAM, more slowly. Enter your machine to see what runs at full speed.
llama.cpp · recommended
version
- Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.macOS / Linux
curl -LsSf https://llama.app/install.sh | shWindowsirm https://llama.app/install.ps1 | iex - Run Nanbeige4.3-33B · needs 23.3 GB memory, 20.8 GB download · from huggingface.co/bartowskichat in the terminal
llama cli -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run Nanbeige4.3-33B · needs 23.3 GB memory, 20.8 GB download · from huggingface.co/bartowski
- Or download it in the terminal
lms get https://huggingface.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF@Q4_K_M -y - Then run lms ls to see its name, and lms chat followed by that name
Ollama
version
- Install Ollama
download it (macOS / Windows) ↗
Linuxcurl -fsSL https://ollama.com/install.sh | sh - Run Nanbeige4.3-33B · needs 23.3 GB memory, 20.8 GB download · from huggingface.co/bartowskichat in the terminal
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q4_K_M
Model repository and documentation: huggingface.co/Nanbeige ↗
$ published results · 11 results, not enough overlap for a score
| test | result | source and conditions |
|---|---|---|
| Terminal-Bench 2.1 | 80.9% | Nanbeige/Nanbeige4.3-33B model card · maker-reported Nanbeige own evaluation, pinned Nanbeige/Nanbeige4.3-33B card (sha df919e1), section '2. Model Performance' table, column 'Nanbeige4.3-33B' (footnote 1: evaluated with preserve_thinking=true in the chat template). Card: 'All models are evaluated at their highest thinking effort. For each benchmark, we use the same inference hyperparameters and harness across models.' Comparison columns (Qwen3.8-27B, Muse-Glimmer-30B, Gemma4-31B) not used. Row 'Terminal-Bench 2.1' (Agentic Coding) = 80.9; footnote 2: 'Terminal-Bench 2.1 is evaluated using Terminus 2.' |
| Terminal-Bench 4.0 | 23.8% | Nanbeige/Nanbeige4.3-33B model card · maker-reported Nanbeige own evaluation, pinned Nanbeige/Nanbeige4.3-33B card (sha df919e1), section '2. Model Performance' table, column 'Nanbeige4.3-33B' (footnote 1: evaluated with preserve_thinking=true in the chat template). Card: 'All models are evaluated at their highest thinking effort. For each benchmark, we use the same inference hyperparameters and harness across models.' Comparison columns (Qwen3.8-27B, Muse-Glimmer-30B, Gemma4-31B) not used. Row 'Terminal-Bench 4.0' (Agentic Coding) = 23.8; footnote 3: 'Terminal-Bench 4 and DeepSWE are evaluated using mini-swe-agent v2.4.6.' |
| SWE-bench Pro (split unspecified) | 60.3% | Nanbeige/Nanbeige4.3-33B model card · maker-reported Nanbeige own evaluation, pinned Nanbeige/Nanbeige4.3-33B card (sha df919e1), section '2. Model Performance' table, column 'Nanbeige4.3-33B' (footnote 1: evaluated with preserve_thinking=true in the chat template). Card: 'All models are evaluated at their highest thinking effort. For each benchmark, we use the same inference hyperparameters and harness across models.' Comparison columns (Qwen3.8-27B, Muse-Glimmer-30B, Gemma4-31B) not used. Row 'SWE-Bench Pro' (Agentic Coding) = 60.3; footnote 3 marker: mini-swe-agent v2.4.6. Public/commercial split not stated, so not mapped to swe-bench-pro. |
| NL2Repo | 53.0% | Nanbeige/Nanbeige4.3-33B model card · maker-reported Nanbeige own evaluation, pinned Nanbeige/Nanbeige4.3-33B card (sha df919e1), section '2. Model Performance' table, column 'Nanbeige4.3-33B' (footnote 1: evaluated with preserve_thinking=true in the chat template). Card: 'All models are evaluated at their highest thinking effort. For each benchmark, we use the same inference hyperparameters and harness across models.' Comparison columns (Qwen3.8-27B, Muse-Glimmer-30B, Gemma4-31B) not used. Row 'NL2Repo' (Agentic Coding) = 53.0; footnote 5: 'NL2Repo is evaluated using Claude Code.' |
| SciCode (level unspecified) | 52.6% | Nanbeige/Nanbeige4.3-33B model card · maker-reported Nanbeige own evaluation, pinned Nanbeige/Nanbeige4.3-33B card (sha df919e1), section '2. Model Performance' table, column 'Nanbeige4.3-33B' (footnote 1: evaluated with preserve_thinking=true in the chat template). Card: 'All models are evaluated at their highest thinking effort. For each benchmark, we use the same inference hyperparameters and harness across models.' Comparison columns (Qwen3.8-27B, Muse-Glimmer-30B, Gemma4-31B) not used. Row 'Scicode' (Agentic Coding) = 52.6; main-vs-subproblem level not stated. |
| AutomationBench v1.0.6 | 54.2% | Nanbeige/Nanbeige4.3-33B model card · maker-reported Nanbeige own evaluation, pinned Nanbeige/Nanbeige4.3-33B card (sha df919e1), section '2. Model Performance' table, column 'Nanbeige4.3-33B' (footnote 1: evaluated with preserve_thinking=true in the chat template). Card: 'All models are evaluated at their highest thinking effort. For each benchmark, we use the same inference hyperparameters and harness across models.' Comparison columns (Qwen3.8-27B, Muse-Glimmer-30B, Gemma4-31B) not used. Row 'Automation Bench' (Agentic Cowork) = 54.2; footnote 6: 'Automation Bench v1.0.6 includes 600 publicly released tasks.' |
| Toolathlon-Verified | 70.4% | Nanbeige/Nanbeige4.3-33B model card · maker-reported Nanbeige own evaluation, pinned Nanbeige/Nanbeige4.3-33B card (sha df919e1), section '2. Model Performance' table, column 'Nanbeige4.3-33B' (footnote 1: evaluated with preserve_thinking=true in the chat template). Card: 'All models are evaluated at their highest thinking effort. For each benchmark, we use the same inference hyperparameters and harness across models.' Comparison columns (Qwen3.8-27B, Muse-Glimmer-30B, Gemma4-31B) not used. Row 'Toolathlon-Verified' (Agentic Cowork) = 70.4; footnote 10: 'Toolathlon-Verified sets no max_tokens limit for individual model requests.' |
| DeepPlanning | 63.3% | Nanbeige/Nanbeige4.3-33B model card · maker-reported Nanbeige own evaluation, pinned Nanbeige/Nanbeige4.3-33B card (sha df919e1), section '2. Model Performance' table, column 'Nanbeige4.3-33B' (footnote 1: evaluated with preserve_thinking=true in the chat template). Card: 'All models are evaluated at their highest thinking effort. For each benchmark, we use the same inference hyperparameters and harness across models.' Comparison columns (Qwen3.8-27B, Muse-Glimmer-30B, Gemma4-31B) not used. Row 'DeepPlanning' (Agentic Cowork) = 63.3; footnote 12: evaluated using the official repository. |
| τ³-bench | 48.8% | Nanbeige/Nanbeige4.3-33B model card · maker-reported Nanbeige own evaluation, pinned Nanbeige/Nanbeige4.3-33B card (sha df919e1), section '2. Model Performance' table, column 'Nanbeige4.3-33B' (footnote 1: evaluated with preserve_thinking=true in the chat template). Card: 'All models are evaluated at their highest thinking effort. For each benchmark, we use the same inference hyperparameters and harness across models.' Comparison columns (Qwen3.8-27B, Muse-Glimmer-30B, Gemma4-31B) not used. Row 'Tau3-Bench' (Agentic Cowork) = 48.8; footnote 12: evaluated using the official repository. Domain average as printed. |
| GPQA Diamond | 89.5% | Nanbeige/Nanbeige4.3-33B model card · maker-reported Nanbeige own evaluation, pinned Nanbeige/Nanbeige4.3-33B card (sha df919e1), section '2. Model Performance' table, column 'Nanbeige4.3-33B' (footnote 1: evaluated with preserve_thinking=true in the chat template). Card: 'All models are evaluated at their highest thinking effort. For each benchmark, we use the same inference hyperparameters and harness across models.' Comparison columns (Qwen3.8-27B, Muse-Glimmer-30B, Gemma4-31B) not used. Row 'GPQA Diamond' (Reasoning) = 89.5. |
| AIME 2026 | 95.2% | Nanbeige/Nanbeige4.3-33B model card · maker-reported Nanbeige own evaluation, pinned Nanbeige/Nanbeige4.3-33B card (sha df919e1), section '2. Model Performance' table, column 'Nanbeige4.3-33B' (footnote 1: evaluated with preserve_thinking=true in the chat template). Card: 'All models are evaluated at their highest thinking effort. For each benchmark, we use the same inference hyperparameters and harness across models.' Comparison columns (Qwen3.8-27B, Muse-Glimmer-30B, Gemma4-31B) not used. Row 'AIME 2026' (Reasoning) = 95.2; I/II split and sampling count not stated. |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json