AutoDecompiler-6.7B-e2e is an open-weight model from AutoDecompiler. It has 266,240 parameters and a 16,384-token context. At 16-bit it needs about 0 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 5 downloads a month.
Runs On
What it takes to serve AutoDecompiler-6.7B-e2e (266,240 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 | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 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.
AutoDecompiler-6.7B-e2e on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- LlamaForCausalLM
- Context length (tokens)
- 16,384
- Layers
- 32
- Hidden size
- 4,096
- Feed-forward size
- 11,008
- Attention heads
- 32
- Key/value heads
- 32
- Head dimension
- 128
- Vocabulary size
- 32,256
- RoPE base
- 100,000
- Model type
- llama
Identity and Version
- Repository
- AutoDecompiler/AutoDecompiler-6.7B-e2e
- Publisher
- AutoDecompiler
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 266,240 parameters
- Languages
- Not stated by the source
- Revision
- cd4535f1dfbc88b65869e79af129b0ec0559a557
- First published
- 2026-05-22
- Last updated
- 2026-10-15
Files and Weights
25 files, 13.5 GB in total. The weights are 13 files totalling 13.5 GB in bin, pt, pth, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00003.safetensors | Weights | 4.9 GB | a4961a69e3d6 |
| model-00002-of-00003.safetensors | Weights | 4.9 GB | a444075d944e |
| model-00003-of-00003.safetensors | Weights | 3.6 GB | ec6b07eed7c1 |
| rng_state_0.pth | Weights | 16.4 KB | ab8aba3f130e |
| rng_state_1.pth | Weights | 16.4 KB | c2c8d1373355 |
| rng_state_2.pth | Weights | 16.4 KB | 3195e26bae15 |
| rng_state_3.pth | Weights | 16.4 KB | d117da7a633b |
| rng_state_4.pth | Weights | 16.4 KB | 98479d5de6b4 |
| rng_state_5.pth | Weights | 16.4 KB | f4d38a3fdb4d |
| rng_state_6.pth | Weights | 16.4 KB | e15407b432ca |
| rng_state_7.pth | Weights | 16.3 KB | 36bc9836cbce |
| scheduler.pt | Weights | 1.5 KB | 2b1276b6b8e1 |
| training_args.bin | Weights | 9.2 KB | eee463c000b0 |
| config.json | Configuration | 774 B | — |
| configuration.json | Configuration | 16 B | — |
| generation_config.json | Configuration | 165 B | — |
| model.safetensors.index.json | Configuration | 24.0 KB | — |
| special_tokens_map.json | Configuration | 466 B | — |
| trainer_state.json | Configuration | 29.5 KB | — |
| zero_to_fp32.py | Configuration | 33.3 KB | — |
| chat_template.jinja | Other | 1.0 KB | — |
| latest | Other | 14 B | — |
| .gitattributes | Repository | 2.1 KB | — |
| tokenizer.json | Tokenizer | 2.3 MB | — |
| tokenizer_config.json | Tokenizer | 4.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 13.5 GB
Released by AutoDecompiler through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 13.5 GB |
| 16-bit | 0.0 GB |
| 8-bit | 0.0 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About AutoDecompiler-6.7B-e2e
How much GPU memory does AutoDecompiler-6.7B-e2e need?
About 0 GB at 16-bit and 0 GB at 4-bit: the weights (266,240 parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run AutoDecompiler-6.7B-e2e 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 AutoDecompiler-6.7B-e2e's context length?
16,384 tokens, from the maximum position embeddings in its published configuration.