Flint-40B-A2.5B-abliterated (BF16 safetensors)

An abliterated (uncensored) Flint: RecursiveSI's Flint 40B-A2.5B with its refusal direction removed, for security research and coding work: exploit analysis, malware triage, detection engineering, CTFs and red-team tooling that the original model often declines.

Summary: held-out MITRE ATT&CK refusals 15% → 0% (n=100, Q8_0). No significant drop on HumanEval+, MBPP+, GSM8K, MMLU-Pro, CyberMetric or WMDP-cyber (paired, same items). KL divergence from the original on harmless prompts: 0.0146. Builds: BF16, GGUF (Q8_0 to Q3_K_M), NVFP4 for NVIDIA Blackwell, MLX 4-bit for Apple silicon.

Which build

Not sure? Take the GGUF Q4_K_M (24 GB). It runs in llama.cpp and in apps built on it, including LM Studio (its llama.cpp runtime 2.63.0 includes Flint). On a Mac, the Rec 4-bit build runs in RecursiveSI's Rec runtime (125 tok/s decode on an M4 Pro) and the MLX 4-bit build in mlx-lm (85 tok/s).

Plan for the file size plus memory for context: about 26 KB per token, so roughly 7 GB at the full 262,144 tokens.

Community builds

Quantizations made by other people. I have not tested them. The model tree on this page links every build that lists this model as its base.

Making your own quant: keep Flint out of FP16. In layer 46 the expert product silu(gate) · up reaches about 90,000, above the FP16 maximum of 65,504, so FP16 builds answer !!!! and give NaN logits. MLX computes in the dtype of the scales and unquantized tensors, so store those in BF16. Studio-Research-M1 found and measured this (discussion).

Results

Both models ran as Q8_0 GGUF on llama-server with the same flags, Flint's recommended sampling (temperature 1.0, top_p 0.95, top_k 20) and full reasoning, on evenly spaced subsets of each benchmark (n in each row). Checks are paired on the same items; a quality check fails only on a drop that is significant at 95%. Refusals are scored with Meta's CyberSecEval refusal check. Refusal rates count refusals only. A reply with no final answer (the model was still reasoning at the 8,192-token limit) is listed separately as "no answer": on the 100 MITRE prompts that happened 19 times for the abliterated model and once for the original. The cut-off reasoning was not repetitive; give long security tasks a larger token budget.

Refusals on held-out CyberSecEval MITRE prompts (n per ATT&CK category below):

Heretic's default refusal count, measured on the NVFP4 builds (100 mlabonne/harmful_behaviors test prompts, reasoning off, greedy, 100 tokens): original 96/100, abliterated 55/100. That count flags any reply containing words such as "harmful" or "illegal", including answers that comply; only 1 of the 55 replies opens with a refusal. Meta's CyberSecEval refusal check on the same replies: original 18/100, abliterated 1/100.

KL divergence from the original on 100 harmless prompts, measured by the search for the selected trial (not part of the checks above): 0.0146 nats/token.

Benchmarks: CyberSecEval MITRE and FRR (Meta), CyberMetric-500, WMDP-cyber, MMLU-Pro, GSM8K, HumanEval+ and MBPP+ (EvalPlus); speed from llama-bench pp512/tg128.

Method

The refusal direction comes from the difference in mean activations on harmful and harmless prompts (mlabonne/harmful_behaviors, mlabonne/harmless_alpaca). abliterix removes it from attention output, shared-expert and routed-expert projections; Optuna picks the strengths over 50 trials against refusals on 100 MITRE prompts and KL divergence on harmless prompts. The MITRE prompts in the table were never seen by the search. Tensor shapes are unchanged, so speed and memory match the original.

Usage

Reasoning is optional. When the model reasons, it uses <think>…</think> before its answer. Use the sampling settings above.

llama.cpp (b11827 or later):

llama-server -m Flint-40B-A2.5B-abliterated-Q8_0.gguf --jinja -ngl 999 -fa on

transformers 5.20 (trust_remote_code=True, the port ships with the weights):

from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "dima6312/Flint-40B-A2.5B-abliterated"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, trust_remote_code=True, dtype="bfloat16", device_map="auto")

Limitations

• The checks ran on subsets of each benchmark (n in each row), on the Q8_0 GGUF only. Short checks (n=10 GSM8K, n=10 HumanEval+): Q4_K_M 9/10 and 9/10. An IQ2_M build scored 0/10 on both and was removed on 2026-11-01. Other quants were not measured.
• Refusals are lower, not zero: the selected trial still refused 10 of the 100 prompts used by the search.
• On long security tasks the model can reason for more than 8,192 tokens before answering.
• Abliteration removes refusals; it adds no knowledge. Mistakes the original makes, this model makes too.

Responsible use

This model answers requests the original refuses. It is meant for authorized security testing, research, education and defensive work. You are responsible for how you use it and for following the law and the terms of the systems you test. Its answers can be wrong; check them before acting on them.

Credits

• Flint by RecursiveSI (Apache 2.0). This is a derivative of their weights under the same license.
• abliterix by wuwangzhang1216, building on Heretic by p-e-w.
• Arditi et al., Refusal in Language Models Is Mediated by a Single Direction (2024).
• Maxime Labonne's harmful/harmless prompt sets; Meta's CyberSecEval; CyberMetric (Tihanyi et al.); WMDP (Center for AI Safety); MMLU-Pro (TIGER-Lab); GSM8K (OpenAI); EvalPlus.
• llama.cpp (ggml-org) and transformers (Hugging Face).