The three-language base with a 2,048-token context: AnuLM-Base-400M continued for 10,000 steps at block 2,048 with YaRN, on 46M tokens of the same Hindi / English / Python proportions it was originally trained on. Five hours on one RTX 5070 Ti. Full log and the honest reading of what it bought: docs/RESULTS.md §28, with the zero-shot measurement it is compared against Hindi and English Wikipedia are CC BY-SA, C4 is ODC-BY, and the Python slice is codeparrot-clean, de-duplicated GitHub Python with mixed licences. Not affiliated with Sarvam AI, AI4Bharat, BharatGen or the Government of India. Every other checkpoint in this project is trained at 512 tokens. This one answers what happens if you…
LFM2.5-350M-TTS-v3 is a model for text generation from Kim (access requested at publisher). It has 383M parameters. At 16-bit it needs about 0.9 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
This model is a fine-tuned version of None. It has been trained using TRL. This model was trained with SFT.
Parameters383M
Context—
Weights765.5 MB
License—
AccessAccess requested at publisher
Monthly Downloads—
Runs On
What it takes to serve LFM2.5-350M-TTS-v3 (383M 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 | 0.8 GB | 0.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.4 GB | 0.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.2 GB | 0.2 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 7, 2026.
LFM2.5-350M-TTS-v3 on every accelerator the SAVRN Index prices, at every precision
Model Card
This model is a fine-tuned version of None. It has been trained using TRL. This model was trained with SFT.
Excerpt from the card by Kim.
Identity and Version
- Repository
- Panga-Azazia/LFM2.5-350M-TTS-v3
- Publisher
- Kim
- Task
- Text generation
- Modality
- Text
- Library
- transformers
- Parameters
- 383M parameters
- Languages
- sft, trl
- Revision
- 8dcb472d8e4b345d093b413423bad1e13c4592f7
- First published
- 2026-09-25
- Last updated
- 2026-09-27
Files and Weights
10 files, 781.3 MB in total. The weights are 2 files totalling 765.5 MB in bin, safetensors.
Weights2 files · 765.5 MB
Configuration3 files · 1.9 KB
Tokenizer2 files · 15.9 MB
Documentation1 file · 1.6 KB
Other1 file · 2.6 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 765.5 MB | — |
| training_args.bin | Weights | 6.4 KB | — |
| config.json | Configuration | 1.3 KB | — |
| generation_config.json | Configuration | 166 B | — |
| special_tokens_map.json | Configuration | 434 B | — |
| README.md | Documentation | 1.6 KB | — |
| chat_template.jinja | Other | 2.6 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 10.4 MB | — |
| tokenizer_config.json | Tokenizer | 5.5 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Access requested at publisher
- Download size
- 765.5 MB
Request access from Kim
Kim grants access through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 765.5 MB |
| 16-bit | 0.8 GB |
| 8-bit | 0.4 GB |
| 4-bit | 0.2 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About LFM2.5-350M-TTS-v3
How much GPU memory does LFM2.5-350M-TTS-v3 need?
About 0.9 GB at 16-bit and 0.2 GB at 4-bit: the weights (383M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run LFM2.5-350M-TTS-v3 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.
Similar Models
SmolLM2Prover is a specialized, fine-tuned version of prithivMLmods/SmolLM2-CoT-360M. While retaining the strong conversational abilities of its base model, this version has been specifically enhanced to excel at deep thinking, logical reasoning, and higher-level mathematics, with a focus on generating step-by-step proofs and explanations (Chain-of-Thought). The model was fine-tuned using multiple rounds of Supervised Fine-Tuning (SFT) with the TRL library on a curated dataset, enhancing its ability to follow complex instructions and reason through problems. This model is intended to be used for text generation tasks that require logical reasoning or advanced conversation. The easiest way…
The Drafter agent of a LangGraph multi-agent support system for the fictional shop ReVonance. Base model HuggingFaceTB/SmolLM2-360M-Instruct, fine-tuned with LoRA (merged). Stage: sft (sft = supervised on the response simulator; dpo = then aligned with human and critic preferences via Direct Preference Optimisation). Knowledge-base fingerprint: f9cdb07b5df6. Demo model trained on synthetic data; it only knows the toy policies of ReVonance.
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
Suggest a title and description for any text. On-device titles and descriptions: a short factual title and a one- to two-sentence description for any passage of text. Swift (requirements) Then add the Title product to your target. The MLX trait is required: without it the module compiles as a stub. Get a title and a one or two sentence description for any passage of text, on device. Fine-tuned on transcript clips, but it works on any prose. The register is deliberately plain, with no emoji, no hashtags and no clickbait, and a description is meant to identify this passage rather than its topic. An MLX model directory. Load the folder, not a single file. The chat template is not incidental. A…