sn97-sft-v1 is an open-weight model from Cristian Ascencion Macias Valdez. It has 36B parameters and a 262,144-token context. At 16-bit it needs about 86.3 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 sn97-sft-v1 (36B 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 | 71.9 GB | 86.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x MI325X $2.00 · 1x MI355X $2.59 |
| 8-bit | 36.0 GB | 43.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 18.0 GB | 21.6 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.
sn97-sft-v1 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_5MoeForConditionalGeneration
- Context length (tokens)
- 262,144
- Layers
- 40
- Hidden size
- 2,048
- Attention heads
- 16
- Key/value heads
- 2
- Head dimension
- 256
- Vocabulary size
- 248,320
- Experts
- 256
- Experts active per token
- 8
- Model type
- qwen3_5_moe
Identity and Version
- Repository
- crismacias/sn97-sft-v1
- Publisher
- Cristian Ascencion Macias Valdez
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 36B parameters
- Languages
- Not stated by the source
- Revision
- a6b697ba14967c567685a31a269b6ec4637e41b2
- First published
- 2026-10-15
- Last updated
- 2026-10-15
Files and Weights
31 files, 71.9 GB in total. The weights are 22 files totalling 71.9 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00022.safetensors | Weights | 3.7 GB | dc3465056607 |
| model-00002-of-00022.safetensors | Weights | 3.4 GB | 8fbb6d85ee06 |
| model-00003-of-00022.safetensors | Weights | 3.4 GB | ef9a10fd8432 |
| model-00004-of-00022.safetensors | Weights | 3.4 GB | 2f960adcbbd1 |
| model-00005-of-00022.safetensors | Weights | 3.4 GB | 281b2c567f38 |
| model-00006-of-00022.safetensors | Weights | 3.4 GB | ff82c1e095da |
| model-00007-of-00022.safetensors | Weights | 3.4 GB | d3f62bad7265 |
| model-00008-of-00022.safetensors | Weights | 3.4 GB | 77b95649fb5b |
| model-00009-of-00022.safetensors | Weights | 3.4 GB | 783209a31893 |
| model-00010-of-00022.safetensors | Weights | 3.4 GB | 14b69eb2b8f2 |
| model-00011-of-00022.safetensors | Weights | 3.4 GB | a9f9868ae38b |
| model-00012-of-00022.safetensors | Weights | 3.4 GB | 777e2184ab10 |
| model-00013-of-00022.safetensors | Weights | 3.4 GB | dc0dd9429f93 |
| model-00014-of-00022.safetensors | Weights | 3.4 GB | 51c7b1385b00 |
| model-00015-of-00022.safetensors | Weights | 3.4 GB | 78e1e3f477ca |
| model-00016-of-00022.safetensors | Weights | 3.4 GB | ad24d63f7be3 |
| model-00017-of-00022.safetensors | Weights | 3.4 GB | 6316f62f2156 |
| model-00018-of-00022.safetensors | Weights | 3.4 GB | 128f8a5518ec |
| model-00019-of-00022.safetensors | Weights | 3.4 GB | 653e19c1e9cb |
| model-00020-of-00022.safetensors | Weights | 3.4 GB | 6052aa7b08e0 |
| model-00021-of-00022.safetensors | Weights | 4.3 GB | cbce7dfe4e2d |
| model-00022-of-00022.safetensors | Weights | 35.7 MB | 729842524080 |
| config.json | Configuration | 3.7 KB | — |
| generation_config.json | Configuration | 202 B | — |
| model.safetensors.index.json | Configuration | 96.3 KB | — |
| preprocessor_config.json | Configuration | 390 B | — |
| video_preprocessor_config.json | Configuration | 385 B | — |
| chat_template.jinja | Other | 7.8 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 12.8 MB | 5f9e4d4901a9 |
| tokenizer_config.json | Tokenizer | 16.7 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 71.9 GB
Released by Cristian Ascencion Macias Valdez through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 71.9 GB |
| 16-bit | 71.9 GB |
| 8-bit | 36.0 GB |
| 4-bit | 18.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About sn97-sft-v1
How much GPU memory does sn97-sft-v1 need?
About 86.3 GB at 16-bit and 21.6 GB at 4-bit: the weights (36B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run sn97-sft-v1 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 sn97-sft-v1's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.