LF

lfm2.5 2.6b fable5 coding agent heretic

LfmGGUF by AzariazIZIUpdated 2026-10-14
Download on Hugging Face
Parameters2.7B
Context128K
Layers30
Architecturelfm2
Smallest quant1.1 GB
Quick answer

lfm2.5 2.6b fable5 coding agent heretic needs about 4.2 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 1.1 GB (Q2_K) to 5.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

LFM2.5 2.6B Fable5 Coding Agent Heretic – compact coding agent with tool‑call generation

LFM2.5 2.6B Fable5 Coding Agent Heretic is a 2.7B parameter model fine‑tuned on Fable‑5 premium data. It supports multi‑turn assistant behavior, code generation, and structured tool‑call generation. The model is released without refusal guardrails and is intended for research and evaluation.

Good at

  • Code generation and explanation
  • Structured tool‑call generation
  • Multi‑turn assistant behavior

Limits

  • No vision support
  • Not production‑ready
  • License is other

Best for

  • Developers building coding assistants
  • Researchers evaluating tool‑use patterns
  • Users needing a compact 2.6B coding agent

Who it’s for. Developers who want a compact 2.6B coding agent with LFM2's hybrid conv+attention architecture. The model is fast for inference, supports tool‑call generation, and is suitable for research and evaluation rather than production use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.1 GB 3.6 GB
Fits Get file →
IQ3_S1.3 GB 3.8 GB
Fits Get file →
Q3_K_S1.3 GB 3.8 GB
Fits Get file →
Q3_K_M1.4 GB 3.9 GB
Fits Get file →
Q3_K_L1.5 GB 4.0 GB
Fits Get file →
IQ4_XS1.5 GB 4.0 GB
Fits Get file →
Q4_01.6 GB 4.1 GB
Fits Get file →
Q4_K_S1.6 GB 4.1 GB
Fits Get file →
Q4_K_M1.7 GB 4.2 GB
Fits Get file →
Q4_11.7 GB 4.3 GB
Fits Get file →
Q5_K_S1.9 GB 4.4 GB
Fits Get file →
Q5_K_M1.9 GB 4.5 GB
Fits Get file →
Q6_K2.2 GB 4.7 GB
Fits Get file →
Q8_02.9 GB 5.4 GB
Fits Get file →
F165.4 GB 7.9 GB
Tight Get file →

For 8 GB VRAM, use Q4_K_M (file size 1.67 GB, estimated 4.2 GB memory at 8 k context). If 6 GB VRAM is available, drop to Q3_K_M (1.37 GB, 3.9 GB memory). For 12 GB VRAM, Q4_K_L (1.45 GB, 4 GB memory) offers a balance between quality and size.

What GPU do you need for lfm2.5 2.6b fable5 coding agent 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 IQ4_XS (1.5 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.9 GB file, about 5.4 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.4 GB file, about 7.9 GB in use).

Which lfm2.5 2.6b fable5 coding agent heretic quant should you choose?

Q4_K_M is the usual starting point for lfm2.5 2.6b fable5 coding agent heretic: it balances file size and quality well. Here it is a 1.7 GB file.

The Q8_0 file is 2.9 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 Q2_K at 1.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters2.7B
Layers30
Trained context131,072 tokens
KV cache (fp16)240 KB per token

Source

Quantized byAzariazIZI
FamilyLfm
Licenseother
Downloads (HF)1,435
Last updated2026-10-14

Frequently asked questions about lfm2.5 2.6b fable5 coding agent heretic

How much VRAM does lfm2.5 2.6b fable5 coding agent heretic need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 1.7 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 2.6b fable5 coding agent heretic on an 8 GB GPU?

Yes, with F16: the 5.4 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of lfm2.5 2.6b fable5 coding agent heretic GGUF?

It depends on the quant: Q2_K is 1.1 GB, IQ3_S is 1.3 GB, Q3_K_S is 1.3 GB, Q3_K_M is 1.4 GB, Q3_K_L is 1.5 GB, IQ4_XS is 1.5 GB and 9 more.

What context length does lfm2.5 2.6b fable5 coding agent heretic support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 lfm2.5 2.6b fable5 coding agent heretic GGUF?

The files are on Hugging Face in the AzariazIZI/lfm2.5-2.6b-fable5-coding-agent-heretic 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 2.6b fable5 coding agent 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 this model on 8 GB VRAM?

Yes, use the Q4_K_M quant which requires about 4.2 GB of VRAM at 8 k context. The file size is 1.67 GB.

Does this model support vision?

No, the model has no vision capabilities.

Is the model safe for production use?

It is not considered production‑ready; it is intended for research and evaluation.

Other GGUFs of lfm2.5-2.6b-fable5-coding-agent

Similar models

Browse all →

More Lfm models

All Lfm →

Other tiny models

All tiny models →