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 7 quants, from 1.5 GB (Q4_0) to 5.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
Private, on‑device meeting summarization with cloud‑level quality
LFM2 2.6B Transcript is a 2.57 billion‑parameter model designed for long‑form transcript summarization. It runs entirely locally on CPU, GPU, or NPU and produces structured summaries in seconds. The model is optimized for private, low‑connectivity workflows.
Good at
- Fast, accurate meeting summaries
- Structured output with key points and action items
- Runs locally on edge devices
Limits
- No vision support
- Single‑turn conversation format
- Requires specific input formatting
Best for
- Internal team meetings
- Sales calls and customer conversations
- Regulated environments where data stays on device
Who it’s for. Developers and teams needing private, on‑device meeting summarization. The model is suitable for edge deployments and offline workflows.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 1.5 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_M | 1.6 GB | 4.1 GB | Fits | Get file → | |
| Q5_K_M | 1.8 GB | 4.3 GB | Fits | Get file → | |
| Q6_K | 2.1 GB | 4.6 GB | Fits | Get file → | |
| Q8_0 | 2.7 GB | 5.2 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, Q4_0 or Q4_K_M (≈4 GB memory at 8 k context) are suitable. If 12 GB VRAM is available, Q5_K_M or Q6_K (≈4.3–4.6 GB) provide higher precision. For maximum quality on 16 GB VRAM, Q8_0 (≈5.2 GB) can be used.
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_0 (1.5 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (2.7 GB file, about 5.2 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 Q4_0 at 1.5 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
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: Q4_0 is 1.5 GB, Q4_K_M is 1.6 GB, Q5_K_M is 1.8 GB, Q6_K is 2.1 GB, Q8_0 is 2.7 GB, BF16 is 5.1 GB and 1 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 LiquidAI/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, use Q4_0 or Q4_K_M quantizations, which require about 4 GB of VRAM at 8 k context.
Does the model support multiple languages?
The model is trained for English only.
Is there a cloud API for this model?
No, the model is intended for fully local inference with no cloud services.