← back to catalog · registered 2026-09-19 15:56

mradermacher/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3-i1-GGUF

mradermacher 8B GGUF MoE
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/mradermacher%2FLFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3-i1-GGUF"
Response includes
  • classification m8
  • files 17
  • author_summary 3242 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 2 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • author=mradermacher (M8 quantization producer)
  • is_gguf=1
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
0
Likes
1
Model age
today
created 2026-09-19

Variants by this author 2 formats · 0 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Quantizations
IQ1 IQ2 IQ3 IQ4 Q2_K Q3_K Q4_K Q6_K
Tags
transformers gguf duo-neural agentic coding function-calling hermes liquid-foundation-model moe abliterated code evalplus

Related

Total size
51.0 GB
Files
17
Quantizations
9
Registered
2026-09-19 15:56
Last updated on HF
2026-09-19 16:28

Files by quantization

Q6_K 1 file 6.48 GB
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.i1-Q6_K.gguf 6.48 GB 25e55e54 download
Q4_K 2 files 9.33 GB
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.i1-Q4_K_M.gguf 4.80 GB b9b12582 download
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.i1-Q4_K_S.gguf 4.53 GB 1c55366e download
IQ4 2 files 8.79 GB
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.i1-IQ4_NL.gguf 4.51 GB 57a658ce download
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.i1-IQ4_XS.gguf 4.27 GB 5c9a86ec download
Q3_K 2 files 7.32 GB
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.i1-Q3_K_M.gguf 3.83 GB 515c9353 download
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.i1-Q3_K_S.gguf 3.50 GB 4e6ee390 download
IQ3 2 files 6.63 GB
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.i1-IQ3_M.gguf 3.52 GB 09b718bb download
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.i1-IQ3_XXS.gguf 3.11 GB cd4fa18b download
Q2_K 2 files 5.72 GB
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.i1-Q2_K.gguf 2.97 GB 10e04b52 download
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.i1-Q2_K_S.gguf 2.75 GB a547e7ad download
IQ2 2 files 4.81 GB
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.i1-IQ2_M.gguf 2.65 GB 4fc1198a download
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.i1-IQ2_XXS.gguf 2.16 GB d07b6c67 download
IQ1 1 file 1.87 GB
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.i1-IQ1_M.gguf 1.87 GB 9863ad6d download
Auxiliary files 3 files 16.6 MB
LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v3.imatrix.gguf 16.6 MB e83c371a download
.gitattributes 2.96 KB 4265e1c3 download
README.md 505 B 723fe632 download

README current version from Hugging Face

Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in app" button that hands off directly to a local runtime of your choice - Infrahuman, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.