LFM2-2.6B-Transcript needs about 4.1 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 31 quants, from 0.0 GB to 5.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
LFM2-2.6B-Transcript – on‑device meeting summarization
LFM2-2.6B-Transcript is a 2.57‑billion‑parameter model optimized for private, on‑device transcript summarization. It runs on CPU, GPU, and NPU hardware and is designed for single‑turn conversations with a structured input format.
Good at
- Summarizing 30‑60 minute meetings
- Producing structured key points and action items
- Running fully locally without internet
Limits
- Requires a 128000‑token context window
- No vision or multi‑modal support
- License type is other, not specified
Best for
- Internal team meeting summaries
- Sales call recap
- Regulated environments needing local processing
Who it’s for. Developers building edge AI applications that need concise meeting summaries without sending data to the cloud. Suitable for mobile, laptop, or vehicle deployments where privacy and low latency are critical.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.5 GB | Fits | Get file → | |
| IQ3_XXS | 1.1 GB | 3.6 GB | Fits | Get file → | |
| IQ3_XS | 1.2 GB | 3.7 GB | Fits | Get file → | |
| IQ3_M | 1.2 GB | 3.7 GB | Fits | Get file → | |
| IQ3_S | 1.2 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_S | 1.3 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_M | 1.4 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_L | 1.4 GB | 3.9 GB | Fits | Get file → | |
| IQ4_XS | 1.4 GB | 3.9 GB | Fits | Get file → | |
| Q4_0 | 1.4 GB | 4.0 GB | Fits | Get file → | |
| IQ4_NL | 1.5 GB | 4.0 GB | Fits | Get file → | |
| Q4_0 | 1.5 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_S | 1.5 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_M | 1.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_1 | 1.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_L | 1.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_1 | 1.7 GB | 4.2 GB | Fits | Get file → | |
| Q5_0 | 1.8 GB | 4.3 GB | Fits | Get file → | |
| Q5_0 | 1.8 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_S | 1.8 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_M | 1.9 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_L | 1.9 GB | 4.4 GB | Fits | Get file → | |
| Q5_1 | 1.9 GB | 4.4 GB | Fits | Get file → | |
| Q5_1 | 2.0 GB | 4.5 GB | Fits | Get file → | |
| Q6_K_M | 2.1 GB | 4.6 GB | Fits | Get file → | |
| Q6_K_L | 2.1 GB | 4.7 GB | Fits | Get file → | |
| Q8_0 | 2.7 GB | 5.2 GB | Fits | Get file → | |
| BF16 | 3.5 GB | 6.0 GB | Fits | Get file → | |
| F16 | 3.5 GB | 6.0 GB | Fits | Get file → | |
| BF16 | 5.1 GB | 7.7 GB | Tight | Get file → | |
| F16 | 5.1 GB | 7.7 GB | Tight | Get file → |
For 8 GB VRAM, use IQ4_0 (1.45 GB) or Q4_K_M (1.58 GB) which need about 4 GB of VRAM at 8 k context. For 4 GB VRAM, IQ3_XS (1.18 GB) or Q3_K_S (1.34 GB) are suitable, estimating 3.6–3.9 GB of VRAM. Larger quantizations such as Q6_K_L (2.14 GB) require 4.7 GB of VRAM and are best for higher‑capacity GPUs.
What GPU do you need for LFM2-2.6B-Transcript?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q4_K_S (1.5 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (3.5 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (5.1 GB file, about 7.7 GB in use).
Which LFM2-2.6B-Transcript quant should you choose?
Q4_K_M is the usual starting point for LFM2-2.6B-Transcript: it balances file size and quality well. Here it is a 1.6 GB file.
The Q8_0 file is 2.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LFM2-2.6B-Transcript
How much VRAM does LFM2-2.6B-Transcript need?
About 4.1 GB at Q4_K_M with an 8K context window. That is the 1.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run LFM2-2.6B-Transcript on an 8 GB GPU?
Yes, with BF16: the 5.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2-2.6B-Transcript GGUF?
It depends on the quant: file is 0.0 GB, IQ3_XXS is 1.1 GB, IQ3_XS is 1.2 GB, IQ3_M is 1.2 GB, IQ3_S is 1.2 GB, Q3_K_S is 1.3 GB and 25 more.
What context length does LFM2-2.6B-Transcript support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.
Where can I download LFM2-2.6B-Transcript GGUF?
The files are on Hugging Face in the Mungert/LFM2-2.6B-Transcript-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does LFM2-2.6B-Transcript use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run LFM2-2.6B-Transcript on 8 GB VRAM?
Yes, quantizations such as IQ4_0 or Q4_K_M fit within 8 GB VRAM, using approximately 4 GB at 8 k context.
Does the model support multi‑turn conversations?
No, it is intended for single‑turn conversations with a specific input format.
What languages does the model support?
The model is trained for English only.