Jeva-9b is an open-weight model from Guilherme Keller2. It has 9.7B parameters and a 262,144-token context. At 16-bit it needs about 23.2 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Bruh Jev is close source... hmmmmm, should i make one myself? YES FOR SURE SOO... Coding sounds Computer almost crashing sounds its here!!! MY SONNN i present you to the world!! - "typenotsafe", 2026
Runs On
What it takes to serve Jeva-9b (9.7B 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 | 19.3 GB | 23.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 9.7 GB | 11.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 4.8 GB | 5.8 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 23, 2026.
Jeva-9b on every accelerator the SAVRN Index prices, at every precision
Model Card
Bruh Jev is close source... hmmmmm, should i make one myself? YES FOR SURE SOO... Coding sounds Computer almost crashing sounds its here!!! MY SONNN i present you to the world!! - "typenotsafe", 2026
Excerpt from the card by Guilherme Keller2.
Configuration
- Architecture
- Qwen3_5ForConditionalGeneration
- Context length (tokens)
- 262,144
- Layers
- 32
- Hidden size
- 4,096
- Feed-forward size
- 12,288
- Attention heads
- 16
- Key/value heads
- 4
- Head dimension
- 256
- Vocabulary size
- 248,320
- Stored precision
- bfloat16
- Model type
- qwen3_5
Identity and Version
- Repository
- Guilherme34/Jeva-9b
- Publisher
- Guilherme Keller2
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 9.7B parameters
- Languages
- Not stated by the source
- Revision
- b0bf1c0a8236c3c69fdf579fc3bafd56f65164e1
- First published
- 2026-10-11
- Last updated
- 2026-10-11
Files and Weights
28 files, 87.8 GB in total. The weights are 14 files totalling 87.7 GB in gguf, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| gguf/mmproj-BF16.gguf | Weights | 921.7 MB | 96caacf061b8 |
| gguf/mmproj-F16.gguf | Weights | 918.2 MB | cf4861695e4c |
| gguf/mmproj-Q8_0.gguf | Weights | 624.2 MB | 2d46b854e933 |
| gguf/model-BF16.gguf | Weights | 18.2 GB | cf1c19771a71 |
| gguf/model-F16.gguf | Weights | 18.2 GB | 282c33291073 |
| gguf/model-Q4_K_M.gguf | Weights | 5.7 GB | 7239e1a4a9ca |
| gguf/model-Q5_K_M.gguf | Weights | 6.6 GB | 5c32dd4e52a2 |
| gguf/model-Q6_K.gguf | Weights | 7.5 GB | 15217397e8d6 |
| gguf/model-Q8_0.gguf | Weights | 9.7 GB | 4c3b614832eb |
| joint_head.safetensors | Weights | 243.5 MB | 3cba4e8d709c |
| model.safetensors-00001-of-00004.safetensors | Weights | 5.3 GB | e22b0f4a6c39 |
| model.safetensors-00002-of-00004.safetensors | Weights | 5.3 GB | 33ffc6a3dd43 |
| model.safetensors-00003-of-00004.safetensors | Weights | 5.4 GB | c9135317bd35 |
| model.safetensors-00004-of-00004.safetensors | Weights | 3.3 GB | 6204dc56a47e |
| config.json | Configuration | 2.8 KB | — |
| generation_config.json | Configuration | 141 B | — |
| gguf/export.json | Configuration | 829 B | — |
| joint_head_config.json | Configuration | 118 B | — |
| joint_schema_model.py | Configuration | 23.3 KB | — |
| model.safetensors.index.json | Configuration | 79.7 KB | — |
| processor_config.json | Configuration | 1.3 KB | — |
| unsloth_decision_config.json | Configuration | 766 B | — |
| LICENSE | Documentation | 11.5 KB | — |
| README.md | Documentation | 333 B | — |
| chat_template.jinja | Other | 7.8 KB | — |
| .gitattributes | Repository | 2.1 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
- 87.7 GB
Released by Guilherme Keller2 through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 87.7 GB |
| 16-bit | 19.3 GB |
| 8-bit | 9.7 GB |
| 4-bit | 4.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Jeva-9b
How much GPU memory does Jeva-9b need?
About 23.2 GB at 16-bit and 5.8 GB at 4-bit: the weights (9.7B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Jeva-9b 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 Jeva-9b's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.