Holo-3.1-4B-W8A8-INT8-SQ is an open-weight model from Aaaaflolep. It has 4.5B parameters and a 262,144-token context. At 16-bit it needs about 10.9 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 Holo-3.1-4B-W8A8-INT8-SQ (4.5B 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 | 9.1 GB | 10.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 4.5 GB | 5.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 2.3 GB | 2.7 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 19, 2026.
Holo-3.1-4B-W8A8-INT8-SQ 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_5ForConditionalGeneration
- Context length (tokens)
- 262,144
- Layers
- 32
- Hidden size
- 2,560
- Feed-forward size
- 9,216
- Attention heads
- 16
- Key/value heads
- 4
- Head dimension
- 256
- Vocabulary size
- 248,320
- Model type
- qwen3_5
- Quantization
- compressed-tensors
Identity and Version
- Repository
- Flolep2607/Holo-3.1-4B-W8A8-INT8-SQ
- Publisher
- Aaaaflolep
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 4.5B parameters
- Languages
- Not stated by the source
- Revision
- 54953fa2024041bedb0acb3e22ecd1947c3584d0
- First published
- 2026-10-06
- Last updated
- 2026-10-06
Files and Weights
8 files, 5.5 GB in total. The weights are 1 file totalling 5.5 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 5.5 GB | a7a4b685ae25 |
| config.json | Configuration | 11.3 KB | — |
| generation_config.json | Configuration | 214 B | — |
| recipe.yaml | Configuration | 852 B | — |
| chat_template.jinja | Other | 7.8 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 20.0 MB | 06b9509352d2 |
| tokenizer_config.json | Tokenizer | 1.1 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 5.5 GB
Released by Aaaaflolep through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 5.5 GB |
| 16-bit | 9.1 GB |
| 8-bit | 4.5 GB |
| 4-bit | 2.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Holo-3.1-4B-W8A8-INT8-SQ
How much GPU memory does Holo-3.1-4B-W8A8-INT8-SQ need?
About 10.9 GB at 16-bit and 2.7 GB at 4-bit: the weights (4.5B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Holo-3.1-4B-W8A8-INT8-SQ 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 Holo-3.1-4B-W8A8-INT8-SQ's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.