moe-ft-020d is an open-weight model from crazyApe. It has 34.7B parameters and a 262,144-token context. At 16-bit it needs about 83.2 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 moe-ft-020d (34.7B 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 | 69.3 GB | 83.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x MI325X $2.00 · 1x MI355X $2.59 |
| 8-bit | 34.7 GB | 41.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 17.3 GB | 20.8 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 19, 2026.
moe-ft-020d 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_5MoeForCausalLM
- 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_text
Identity and Version
- Repository
- crazyape777/moe-ft-020d
- Publisher
- crazyApe
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 34.7B parameters
- Languages
- Not stated by the source
- Revision
- 7aaae7ae2961e7b103e9230dd992813af1852ea2
- First published
- 2026-09-22
- Last updated
- 2026-09-22
Files and Weights
25 files, 69.3 GB in total. The weights are 18 files totalling 69.3 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00018.safetensors | Weights | 4.1 GB | 41ad01c0c6e3 |
| model-00002-of-00018.safetensors | Weights | 4.2 GB | ae55977d9543 |
| model-00003-of-00018.safetensors | Weights | 2.1 GB | 289736fb7448 |
| model-00004-of-00018.safetensors | Weights | 4.3 GB | fba197a364e8 |
| model-00005-of-00018.safetensors | Weights | 4.3 GB | 37627ecb1e88 |
| model-00006-of-00018.safetensors | Weights | 3.2 GB | 0d9c97cb02a6 |
| model-00007-of-00018.safetensors | Weights | 4.2 GB | 9ade83e3839e |
| model-00008-of-00018.safetensors | Weights | 4.3 GB | 49b33e763468 |
| model-00009-of-00018.safetensors | Weights | 3.2 GB | bfcb786040bd |
| model-00010-of-00018.safetensors | Weights | 4.2 GB | 277ca080711f |
| model-00011-of-00018.safetensors | Weights | 4.3 GB | cf6a62d146b5 |
| model-00012-of-00018.safetensors | Weights | 3.2 GB | d3bf45b2d310 |
| model-00013-of-00018.safetensors | Weights | 4.2 GB | 4084328e27f9 |
| model-00014-of-00018.safetensors | Weights | 4.3 GB | 11fabab9ee5b |
| model-00015-of-00018.safetensors | Weights | 3.2 GB | 6e402e2505fc |
| model-00016-of-00018.safetensors | Weights | 4.2 GB | 7e36135ab2c0 |
| model-00017-of-00018.safetensors | Weights | 4.3 GB | 4b16a49d1eb5 |
| model-00018-of-00018.safetensors | Weights | 3.2 GB | d77ee54bfc56 |
| config.json | Configuration | 2.3 KB | — |
| generation_config.json | Configuration | 213 B | — |
| model.safetensors.index.json | Configuration | 59.3 KB | — |
| chat_template.jinja | Other | 7.8 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 20.0 MB | 06b9509352d2 |
| tokenizer_config.json | Tokenizer | 1.2 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 69.3 GB
Released by crazyApe through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 69.3 GB |
| 16-bit | 69.3 GB |
| 8-bit | 34.7 GB |
| 4-bit | 17.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About moe-ft-020d
How much GPU memory does moe-ft-020d need?
About 83.2 GB at 16-bit and 20.8 GB at 4-bit: the weights (34.7B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run moe-ft-020d 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 moe-ft-020d's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.