Get the app
← back to catalog · registered 2026-08-22 13:56

KebalBaguette/Mistral-Nemo-Instruct-2407-abliterated-AWQ

KebalBaguette Mistral 11B second-order
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model. 

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/KebalBaguette%2FMistral-Nemo-Instruct-2407-abliterated-AWQ"
Response includes
  • classification m1
  • files 12
  • benchmarks 16 entries
  • hub_downloads_all_time 71,022
  • author_summary 4 models
  • readme_text full
Try next
GET/models?author=KebalBaguette
All 4 models by KebalBaguette
 GET/models?family=mistral&method=m1
Sibling mistral models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 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.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
71K
59 last 30d - cooling
Likes
1
Model age
4mo ago
created 2026-05-19
Downloads over time
Now71.1K→from1.3K↑5,447%
026K52.1K78.1K1.3K on May 2071.1K on Oct 12MayJunJulAugSepOct
May 20 → Oct 12 · 61 snapshots · spans 145 days

Benchmarks

Benchmark Score Source
BBH average 0.45868465430016864 OpenLLM-v2
IFEval instruct 0.6906474820143885 OpenLLM-v2
IFEval-Prompt 0.5878003696857671 OpenLLM-v2
MATH lvl 5 0.05664652567975831 OpenLLM-v2
MMLU-Pro 0.351811835106383 OpenLLM-v2
Entertainment 1.1 UGI
Hazardous 2.9 UGI
Natural Intelligence 23.7 UGI
Political lean -19.9% UGI
Sensitive-Info 17.93 UGI
SocPol 1.7 UGI
UGI 31.12 UGI
Willingness (10) 5.8 UGI
W10-Adherence 4.5 UGI
W10-Direct 7 UGI
Writing 38.9 UGI

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

natong19/Mistral-Nemo-Instruct-2407-abliterated↓ 1,032 this lineage
KebalBaguette/Mistral-Nemo-Instruct-2407-abliterated-AWQ↓ 59

Metadata

License
apache-2.0
Languages
fr en es de ru it pt zh ja
Tags
safetensors mistral abliterated uncensored awq compressed-tensors quantized fr en es de ru

Related

Other by KebalBaguette
Qwen2.5-7B-Instruct-abliterated-v2-AWQ 3K aya-expanse-8b-abliterated-AWQ 11 Mistral-7B-Instruct-v0.3-abliterated-AWQ 10
Same base model
mradermacher/Mistral-Nemo-Instruct-2407-abliterated-GGUF 2K mradermacher/Mistral-Nemo-Instruct-2407-abliterated-i1-GGUF 2K 3uer/Mistral-Nemo-Instruct-2407-abliterated-i1-GGUF 605 Flamesline/Mistral-Nemo-Instruct-2407-abliterated-Q4_K_M-GGUF 184 noneUsername/Mistral-Nemo-Instruct-2407-abliterated-W8A8-Dynamic-Per-Token 9
Total size
7.78 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-05-24 09:56
Source huggingface.co/KebalBaguette/Mistral-Nemo-Instruct-2407-abliterated-AWQ ↗ Base model natong19/Mistral-Nemo-Instruct-2407-abliterated →

Files by quantization

Auxiliary files 12 files 7.79 GB
model-00001-of-00002.safetensors 4.64 GB 567abfa2 download
model-00002-of-00002.safetensors 3.13 GB 3f78cb5b download
tokenizer.json 16.3 MB 1f1fe8be download
tokenizer_config.json 173 KB d1627b69 download
model.safetensors.index.json 104 KB bd0d2cf5 download
chat_template.jinja 3.69 KB df6f656e download
README.md 1.66 KB 952f6790 download
config.json 1.58 KB 8a9383ae download
.gitattributes 1.53 KB 52373fe2 download
recipe.yaml 822 B 1e452d78 download
special_tokens_map.json 552 B a782b2f1 download
generation_config.json 158 B 2621e46d download

README current version from Hugging Face

license: apache-2.0
base_model: natong19/Mistral-Nemo-Instruct-2407-abliterated
tags:

  • mistral
  • abliterated
  • uncensored
  • awq
  • compressed-tensors
  • quantized
    language:
  • fr
  • en
  • es
  • de
  • ru
  • it
  • pt
  • zh
  • ja

Mistral Nemo Instruct 2407 Abliterated — AWQ (W4A16)

AWQ 4-bit quantization of natong19/Mistral-Nemo-Instruct-2407-abliterated,
itself an abliteration of Mistral Nemo Instruct 2407.

Why this exists

The base abliterated model was only published in BF16 and GGUF. This AWQ quant
is ~7 GB VRAM and serves natively in vLLM with the Marlin kernel for fast inference.

Quantization details

  • Tool: llm-compressor (vLLM project)
  • Format: compressed-tensors (auto-detected by vLLM)
  • Scheme: W4A16_ASYM (4-bit asymmetric weights, group_size 128, 16-bit activations)
  • Algorithm: AWQ (Activation-aware Weight Quantization)
  • Calibration: 128 French samples × 192 tokens from wikimedia/wikipedia (20231101.fr)
  • lm_head left in fp16 (preserves output quality)
  • Note: v_proj → o_proj smoothing is skipped on all 40 layers due to GQA shape mismatch
    (32 query heads / 8 KV heads). This is standard AWQ behaviour for GQA models — quality
    impact is marginal since the input_layernorm → q/k/v smoothing remains active.

Usage with vLLM

vllm serve KebalBaguette/Mistral-Nemo-Instruct-2407-abliterated-AWQ \
  --quantization compressed-tensors \
  --max-model-len 8192

License

Apache 2.0, inherited from Mistral Nemo and the abliterated base.

README history 2 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-05-24Update README.md4b8e8c21.7 KB
    Loading...
  2. 2026-05-19Initial AWQ 4-bit quantization with FR calibration2584f5d1.6 KB
    Loading...
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 Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration