KTT-LFM2.5-2.6B-4bit is an open-weight model from Anar Zan. It has 2.7B parameters and a 131,072-token context. At 16-bit it needs about 6.5 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 KTT-LFM2.5-2.6B-4bit (2.7B 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 | 5.4 GB | 6.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 2.7 GB | 3.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 1.3 GB | 1.6 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.
KTT-LFM2.5-2.6B-4bit 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)
- 131,072
- Layers
- 30
- Hidden size
- 2,048
- Feed-forward size
- 10,752
- Attention heads
- 32
- Key/value heads
- 8
- Vocabulary size
- 128,000
- Model type
- lfm2
- Quantization
- bitsandbytes
Identity and Version
- Repository
- AnarZan/KTT-LFM2.5-2.6B-4bit
- Publisher
- Anar Zan
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 2.7B parameters
- Languages
- Not stated by the source
- Revision
- a442d642e59f772c476f67edcd6422c59f4ddfec
- First published
- 2026-09-29
- Last updated
- 2026-09-29
Files and Weights
7 files, 1.8 GB in total. The weights are 1 file totalling 1.8 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.8 GB | b3a7ce4a5b8a |
| config.json | Configuration | 1.9 KB | — |
| generation_config.json | Configuration | 327 B | — |
| chat_template.jinja | Other | 5.4 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 17.9 MB | 695be7802a0e |
| tokenizer_config.json | Tokenizer | 364 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 1.8 GB
Released by Anar Zan through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.8 GB |
| 16-bit | 5.4 GB |
| 8-bit | 2.7 GB |
| 4-bit | 1.3 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About KTT-LFM2.5-2.6B-4bit
How much GPU memory does KTT-LFM2.5-2.6B-4bit need?
About 6.5 GB at 16-bit and 1.6 GB at 4-bit: the weights (2.7B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run KTT-LFM2.5-2.6B-4bit 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 KTT-LFM2.5-2.6B-4bit's context length?
131,072 tokens, from the maximum position embeddings in its published configuration.