lfm2.5-230m-bookstore-agent is an open-weight model from Aaaaflolep. It has 230M parameters and a 128,000-token context. At 16-bit it needs about 0.6 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 2 downloads a month.
Runs On
What it takes to serve lfm2.5-230m-bookstore-agent (230M 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 | 0.5 GB | 0.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.2 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.1 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.
lfm2.5-230m-bookstore-agent on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Lfm2ForCausalLM
- Context length (tokens)
- 128,000
- Layers
- 14
- Hidden size
- 1,024
- Feed-forward size
- 2,560
- Attention heads
- 16
- Key/value heads
- 8
- Vocabulary size
- 65,536
- Model type
- lfm2
Identity and Version
- Repository
- Flolep2607/lfm2.5-230m-bookstore-agent
- Publisher
- Aaaaflolep
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 230M parameters
- Languages
- Not stated by the source
- Revision
- c456d82ab56ebfa012ab0d9830a2e0bb75191ab7
- First published
- 2026-09-22
- Last updated
- 2026-09-24
Files and Weights
65 files, 4.1 GB in total. The weights are 22 files totalling 4.0 GB in bin, pt, pth, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| ckpt/g2-8b-lora/adapter_model.safetensors | Weights | 45.6 MB | 971cf0e75692 |
| ckpt/g2-8b-lora/optimizer.pt | Weights | 91.3 MB | a6b11b200b6a |
| ckpt/g2-8b-lora/rng_state.pth | Weights | 14.6 KB | 12e15e837284 |
| ckpt/g2-8b-lora/scheduler.pt | Weights | 1.5 KB | cd4fc5304525 |
| ckpt/g2-8b-lora/training_args.bin | Weights | 5.8 KB | 77925d5620f6 |
| ckpt/x2-8b-extract-lora/adapter_model.safetensors | Weights | 45.6 MB | ab971c2397bf |
| ckpt/x2-8b-extract-lora/optimizer.pt | Weights | 91.3 MB | faac61891c3a |
| ckpt/x2-8b-extract-lora/rng_state.pth | Weights | 14.6 KB | cde881b24af8 |
| ckpt/x2-8b-extract-lora/scheduler.pt | Weights | 1.5 KB | 0650f9f51d60 |
| ckpt/x2-8b-extract-lora/training_args.bin | Weights | 5.8 KB | bca20463dbda |
| fast-route/model.safetensors | Weights | 918.8 MB | 05d90c6d57bf |
| fast-route/training_args.bin | Weights | 5.7 KB | 40339481fb88 |
| g1-8b-lora/adapter_model.safetensors | Weights | 22.8 MB | ee75a1acb5ff |
| g1-8b-lora/training_args.bin | Weights | 5.8 KB | 14bbddb73daf |
| model.safetensors | Weights | 918.8 MB | ec2c0369238c |
| training_args.bin | Weights | 5.7 KB | 85770cf1e08b |
| v3-home/model.safetensors | Weights | 918.8 MB | 0e31b66b9dd7 |
| v3-home/training_args.bin | Weights | 5.7 KB | 4fb568e37730 |
| v4-backtrack/model.safetensors | Weights | 918.8 MB | 43aacc3af364 |
| v4-backtrack/training_args.bin | Weights | 5.7 KB | 4bb1da8a330f |
| x1-8b-extract-lora/adapter_model.safetensors | Weights | 22.8 MB | aa295f422059 |
| x1-8b-extract-lora/training_args.bin | Weights | 5.8 KB | 09e0f996453b |
| ckpt/g2-8b-lora/adapter_config.json | Configuration | 1.2 KB | — |
| ckpt/g2-8b-lora/trainer_state.json | Configuration | 10.6 KB | — |
| ckpt/x2-8b-extract-lora/adapter_config.json | Configuration | 1.2 KB | — |
| ckpt/x2-8b-extract-lora/trainer_state.json | Configuration | 5.7 KB | — |
| config.json | Configuration | 1.5 KB | — |
| fast-route/config.json | Configuration | 1.5 KB | — |
| fast-route/generation_config.json | Configuration | 314 B | — |
| g1-8b-lora/adapter_config.json | Configuration | 1.2 KB | — |
| generation_config.json | Configuration | 314 B | — |
| v3-home/config.json | Configuration | 1.5 KB | — |
| v3-home/generation_config.json | Configuration | 314 B | — |
| v4-backtrack/config.json | Configuration | 1.5 KB | — |
| v4-backtrack/generation_config.json | Configuration | 314 B | — |
| x1-8b-extract-lora/adapter_config.json | Configuration | 1.2 KB | — |
| ckpt/g2-8b-lora/README.md | Documentation | 5.2 KB | — |
| ckpt/x2-8b-extract-lora/README.md | Documentation | 5.2 KB | — |
| g1-8b-lora/README.md | Documentation | 5.2 KB | — |
| x1-8b-extract-lora/README.md | Documentation | 5.2 KB | — |
| chat_template.jinja | Other | 4.8 KB | — |
| ckpt/g2-8b-lora/chat_template.jinja | Other | 4.8 KB | — |
| ckpt/x2-8b-extract-lora/chat_template.jinja | Other | 4.8 KB | — |
| fast-route/chat_template.jinja | Other | 4.8 KB | — |
| g1-8b-lora/chat_template.jinja | Other | 4.8 KB | — |
| v3-home/chat_template.jinja | Other | 4.8 KB | — |
| v4-backtrack/chat_template.jinja | Other | 4.8 KB | — |
| x1-8b-extract-lora/chat_template.jinja | Other | 4.8 KB | — |
| .gitattributes | Repository | 1.9 KB | — |
| ckpt/g2-8b-lora/tokenizer.json | Tokenizer | 17.9 MB | 695be7802a0e |
| ckpt/g2-8b-lora/tokenizer_config.json | Tokenizer | 345 B | — |
| ckpt/x2-8b-extract-lora/tokenizer.json | Tokenizer | 17.9 MB | 695be7802a0e |
| ckpt/x2-8b-extract-lora/tokenizer_config.json | Tokenizer | 345 B | — |
| fast-route/tokenizer.json | Tokenizer | 4.7 MB | — |
| fast-route/tokenizer_config.json | Tokenizer | 519 B | — |
| g1-8b-lora/tokenizer.json | Tokenizer | 17.9 MB | 695be7802a0e |
| g1-8b-lora/tokenizer_config.json | Tokenizer | 345 B | — |
| tokenizer.json | Tokenizer | 4.7 MB | — |
| tokenizer_config.json | Tokenizer | 519 B | — |
| v3-home/tokenizer.json | Tokenizer | 4.7 MB | — |
| v3-home/tokenizer_config.json | Tokenizer | 519 B | — |
| v4-backtrack/tokenizer.json | Tokenizer | 4.7 MB | — |
| v4-backtrack/tokenizer_config.json | Tokenizer | 519 B | — |
| x1-8b-extract-lora/tokenizer.json | Tokenizer | 17.9 MB | 695be7802a0e |
| x1-8b-extract-lora/tokenizer_config.json | Tokenizer | 345 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 4.0 GB
Released by Aaaaflolep through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 4.0 GB |
| 16-bit | 0.5 GB |
| 8-bit | 0.2 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About lfm2.5-230m-bookstore-agent
How much GPU memory does lfm2.5-230m-bookstore-agent need?
About 0.6 GB at 16-bit and 0.1 GB at 4-bit: the weights (230M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run lfm2.5-230m-bookstore-agent 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 lfm2.5-230m-bookstore-agent's context length?
128,000 tokens, from the maximum position embeddings in its published configuration.