Open-weight model
Ternary-Bonsai-2-primal-bf16
by Kevin willbur devildogwillbur/Ternary-Bonsai-2-primal-bf16
Ternary-Bonsai-2-primal-bf16 is an open-weight model from Kevin willbur. It has 26.9B parameters and a 262,144-token context. At 16-bit it needs about 64.6 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Runs On
What it takes to serve Ternary-Bonsai-2-primal-bf16 (26.9B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 53.8 GB | 64.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 26.9 GB | 32.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 13.4 GB | 16.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 18, 2026.
Ternary-Bonsai-2-primal-bf16 on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Qwen3_5ForCausalLM
- Context length (tokens)
- 262,144
- Layers
- 64
- Hidden size
- 5,120
- Feed-forward size
- 17,408
- Attention heads
- 24
- Key/value heads
- 4
- Head dimension
- 256
- Vocabulary size
- 248,320
- Model type
- qwen3_5_text
Identity and Version
- Repository
- devildogwillbur/Ternary-Bonsai-2-primal-bf16
- Publisher
- Kevin willbur
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 26.9B parameters
- Languages
- Not stated by the source
- Revision
- 6b6c50e12a8215a8773c4060844c436c1ba60b33
- First published
- 2026-10-14
- Last updated
- 2026-10-14
Files and Weights
20 files, 53.8 GB in total. The weights are 12 files totalling 53.8 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00012.safetensors | Weights | 5.1 GB | 036a39e80811 |
| model-00002-of-00012.safetensors | Weights | 4.7 GB | ef8de42e8365 |
| model-00003-of-00012.safetensors | Weights | 4.7 GB | 25c886dc9387 |
| model-00004-of-00012.safetensors | Weights | 4.8 GB | be67448846ab |
| model-00005-of-00012.safetensors | Weights | 4.7 GB | e235af494b0e |
| model-00006-of-00012.safetensors | Weights | 4.7 GB | 4cc0415af631 |
| model-00007-of-00012.safetensors | Weights | 4.8 GB | 8f5089faed6a |
| model-00008-of-00012.safetensors | Weights | 4.8 GB | 1aef92c93279 |
| model-00009-of-00012.safetensors | Weights | 4.7 GB | 245073b88c5f |
| model-00010-of-00012.safetensors | Weights | 4.7 GB | c935f72db2a5 |
| model-00011-of-00012.safetensors | Weights | 4.7 GB | f72b295a15f3 |
| model-00012-of-00012.safetensors | Weights | 1.3 GB | eae9ea4973ca |
| config.json | Configuration | 2.6 KB | — |
| generation_config.json | Configuration | 202 B | — |
| model.safetensors.index.json | Configuration | 70.3 KB | — |
| run_info.json | Configuration | 234 B | — |
| chat_template.jinja | Other | 9.0 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 12.8 MB | 0997f410c57a |
| tokenizer_config.json | Tokenizer | 17.9 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 53.8 GB
Released by Kevin willbur through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 53.8 GB |
| 16-bit | 53.8 GB |
| 8-bit | 26.9 GB |
| 4-bit | 13.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Ternary-Bonsai-2-primal-bf16
How much GPU memory does Ternary-Bonsai-2-primal-bf16 need?
About 64.6 GB at 16-bit and 16.1 GB at 4-bit: the weights (26.9B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Ternary-Bonsai-2-primal-bf16 on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
What is Ternary-Bonsai-2-primal-bf16's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.