LFM2.5 8B A1B Heretic needs about 7.3 GB of memory at Q4_K_M (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 7.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
LFM2.5 8B A1B Heretic – a hybrid MoE model for on‑device use
LFM2.5 8B A1B Heretic is a 8.47 billion‑parameter hybrid model with 1 billion active parameters. It supports a 128 000‑token context and is optimized for tool‑calling and reasoning tasks. The model is available in multiple GGUF quantizations.
Good at
- Tool‑calling
- Reasoning
- Coding
Limits
- No vision support
- Requires updated tokenizer
- License is other
Best for
- Personal assistants
- Agentic instruction following
- On‑device inference
Who it’s for. Developers building lightweight, on‑device assistants that need strong reasoning and coding abilities. The model is suitable for CPU and GPU inference via llama.cpp, MLX, vLLM, and SGLang.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.1 GB | Fits | Get file → | |
| IQ1_S | 1.8 GB | 3.9 GB | Fits | Get file → | |
| IQ1_M | 2.0 GB | 4.1 GB | Fits | Get file → | |
| IQ2_XXS | 2.3 GB | 4.4 GB | Fits | Get file → | |
| IQ2_XS | 2.6 GB | 4.7 GB | Fits | Get file → | |
| IQ2_S | 2.6 GB | 4.7 GB | Fits | Get file → | |
| IQ2_M | 2.8 GB | 5.0 GB | Fits | Get file → | |
| Q2_K_S | 3.0 GB | 5.1 GB | Fits | Get file → | |
| Q2_K | 3.2 GB | 5.3 GB | Fits | Get file → | |
| IQ3_XXS | 3.3 GB | 5.4 GB | Fits | Get file → | |
| IQ3_XS | 3.6 GB | 5.7 GB | Fits | Get file → | |
| IQ3_S | 3.8 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_S | 3.8 GB | 5.9 GB | Fits | Get file → | |
| IQ3_M | 3.8 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_M | 4.1 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_L | 4.4 GB | 6.5 GB | Fits | Get file → | |
| IQ4_XS | 4.6 GB | 6.7 GB | Fits | Get file → | |
| IQ4_NL | 4.8 GB | 7.0 GB | Fits | Get file → | |
| Q4_0 | 4.9 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_S | 4.9 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_M | 5.2 GB | 7.3 GB | Tight | Get file → | |
| Q4_1 | 5.4 GB | 7.5 GB | Tight | Get file → | |
| Q5_K_S | 5.9 GB | 8.0 GB | Tight | Get file → | |
| Q5_K_M | 6.0 GB | 8.1 GB | Too big | Get file → | |
| Q6_K | 7.0 GB | 9.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (5.16 GB file, 7.3 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (6.03 GB file, 8.1 GB memory). For 16 GB VRAM, Q6_K (6.96 GB file, 9.1 GB memory). Estimates are approximate.
What GPU do you need for LFM2.5 8B A1B Heretic?
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 IQ1_S (1.8 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_M (3.8 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_S (5.9 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (7.0 GB file, about 9.1 GB in use).
Which LFM2.5 8B A1B Heretic quant should you choose?
Q4_K_M is the usual starting point for LFM2.5 8B A1B Heretic: it balances file size and quality well. Here it is a 5.2 GB file.
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 LFM2.5 8B A1B Heretic
How much VRAM does LFM2.5 8B A1B Heretic need?
About 7.3 GB at Q4_K_M with an 8K context window. That is the 5.2 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 LFM2.5 8B A1B Heretic on an 8 GB GPU?
Yes, with Q5_K_S: the 5.9 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2.5 8B A1B Heretic GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.8 GB, IQ1_M is 2.0 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.6 GB and 19 more.
What context length does LFM2.5 8B A1B Heretic support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download LFM2.5 8B A1B Heretic GGUF?
The files are on Hugging Face in the mradermacher/LFM2.5-8B-A1B-heretic-i1-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 LFM2.5 8B A1B Heretic 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 LFM2.5 8B A1B on 8 GB VRAM?
Use the Q4_K_M quant. It requires about 7.3 GB of VRAM at 8 k context, which fits within 8 GB.
Does the model support vision?
No, the model is text‑only and has no vision capability.
Do I need to update the tokenizer?
Yes, if you downloaded the model before commit feb5e04, re‑download the tokenizer files to avoid tool‑calling issues.