LF

LFM2.5 8B A1B Hermes Agentic Coder Abliterated

LfmGGUF by DuoNeuralUpdated 2026-09-18
Download on Hugging Face
Parameters8.47B
Context125K
Layers24
Architecturelfm2moe
Smallest quant5.2 GB
Quick answer

LFM2.5 8B A1B Hermes Agentic Coder Abliterated 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 5 quants, from 5.2 GB (Q4_K_M) to 16.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

LFM2.5 8B A1B Hermes Agentic Coder Abliterated – 8.47B hybrid Mamba/attention MoE model

LFM2.5 8B A1B Hermes Agentic Coder Abliterated is a hybrid recurrent/attention architecture with 24 layers, 6 full‑attention layers and 18 convolutional/Mamba MoE layers. It retains 100% of the original model’s factual accuracy, JSON generation, math reasoning and coherent chat quality.

Good at

  • coding
  • reasoning
  • tools

Limits

  • no vision support
  • trained context 128000 tokens
  • license other

Best for

  • autonomous coding agents
  • tool‑integrated workflows
  • reasoning‑heavy tasks

Who it’s for. Developers and researchers needing a high‑performance, agentic coding model with full reasoning capabilities. The model is suitable for building autonomous agents that generate and execute code, handle tool calls, and reason through complex problems.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M5.2 GB 7.3 GB
Tight Get file →
Q5_K_M6.0 GB 8.1 GB
Too big Get file →
Q6_K7.0 GB 9.1 GB
Too big Get file →
Q8_09.0 GB 11.1 GB
Too big Get file →
BF1616.9 GB 19.1 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (5.16 GB, ~7.3 GB memory at 8 k context). If more VRAM is available, Q5_K_M (6.03 GB, ~8.1 GB memory) or Q6_K (6.96 GB, ~9.1 GB memory) provide higher quality. BF16 requires 16.95 GB and ~19.1 GB memory.

What GPU do you need for LFM2.5 8B A1B Hermes Agentic Coder Abliterated?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q4_K_M (5.2 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 11.1 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (16.9 GB file, about 19.1 GB in use).

Which LFM2.5 8B A1B Hermes Agentic Coder Abliterated quant should you choose?

Q4_K_M is the usual starting point for LFM2.5 8B A1B Hermes Agentic Coder Abliterated: it balances file size and quality well. Here it is a 5.2 GB file.

The Q8_0 file is 9.0 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2moe
Parameters8.47B (approximate, mixture of experts)
Active parameters1B
Layers24
Trained context128,000 tokens
KV cache (fp16)192 KB per token

Source

Quantized byDuoNeural
FamilyLfm
Licenseother
Downloads (HF)963
Last updated2026-09-18

Frequently asked questions about LFM2.5 8B A1B Hermes Agentic Coder Abliterated

How much VRAM does LFM2.5 8B A1B Hermes Agentic Coder Abliterated 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 Hermes Agentic Coder Abliterated on an 8 GB GPU?

Yes, with Q4_K_M: the 5.2 GB file needs about 7.3 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 Hermes Agentic Coder Abliterated GGUF?

It depends on the quant: Q4_K_M is 5.2 GB, Q5_K_M is 6.0 GB, Q6_K is 7.0 GB, Q8_0 is 9.0 GB, BF16 is 16.9 GB.

What context length does LFM2.5 8B A1B Hermes Agentic Coder Abliterated 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 Hermes Agentic Coder Abliterated GGUF?

The files are on Hugging Face in the DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-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 Hermes Agentic Coder Abliterated 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, Q4_K_M quantization fits in 8 GB VRAM with an estimated 7.3 GB memory usage at 8 k context.

Does the model support vision?

No, the model has no vision capability.

What is the context length?

The model was trained with 128000 context tokens.

Other GGUFs of LFM2.5-8B-A1B-Abliterated

Similar models

Browse all →

More from DuoNeural

All by DuoNeural →

More Lfm models

All Lfm →

Other small models

All small models →