GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
BlackwellBoy
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
BlackwellBoy
Model Tree
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16
Input Modalities
Output Modalities
Supported Functionality
release-manifest.json for exact uploaded sizes and hashes.All figures below count judge-labeled REFUSAL, not incorrect answers, partial answers or attack success. Lower refusal is not equivalent to higher answer quality.
| Prompt bucket | BOLTBREAKER | Stock Super-VL-120B NVFP4 |
|---|---|---|
| Cyber / pentest, 30 prompts | 3/30 (10.0%) | 16/30 (53.3%) |
| General harm, 94 prompts | 44/94 (46.8%) | 92/94 (97.9%) |
| Benign over-refusal, 45 prompts | 1/45 (2.2%) | 3/45 (6.7%) |
BOLTBREAKER still refused nearly half of the general-harm bucket. Do not describe this release as zero-refusal or fully uncensored.
The cyber breakdown matters: BOLTBREAKER received 13 COMPLY / 14 PARTIAL / 3 REFUSAL, compared with the stock baseline's 1 COMPLY / 13 PARTIAL / 16 REFUSAL. Partial answers are counted separately from both compliance and refusal.
Benign answers were 41 COMPLY / 3 PARTIAL / 1 REFUSAL for BOLTBREAKER, versus 39 COMPLY / 2 PARTIAL / 3 REFUSAL / 1 UNCLEAR for the stock baseline.
evaluation/scores_baseline.json for the BOLTBREAKER and stock baseline label counts. Raw prompt/response transcripts are not included in this release.During build validation, the unedited Bolt source was loaded through the same NF4 workflow and scored 51/64 on a fixed MMLU sample; the final edit scored 50/64. Eight short text checks and a fresh-process reload passed. A separate 32-prompt, 40-token prefix audit changed from 32 detected refusals to 1.
That short-prefix audit is not interchangeable with the later 169-prompt, model-judged evaluation. Use the broader results above when describing refusal behavior. The published NVIDIA BF16 model's full benchmark suite has not been rerun here.
Try BOLTBREAKER if you have Spark-class memory, want a Hugging Face NF4 artifact with unmodified vision components, and care about the lower benign over-refusal observed in this sample.
This BOLTBREAKER checkpoint does not fit entirely in a 32 GiB RTX 5090. No speed advantage, quality advantage from precision, or universal superiority is claimed.
This is a custom-code Transformers/bitsandbytes NF4 checkpoint, not GGUF. It is not validated as a drop-in model for Ollama, llama.cpp, stock vLLM, or every Transformers environment.
The validated runtime used ARM64 Python 3.12.3, CUDA PyTorch 2.14.0+cu130, Transformers 5.19.0, bitsandbytes 0.50.2, accelerate 1.15.0 and safetensors 0.8.0. See runtime-manifest.json and RUNTIME.txt. The required native/Triton dependencies make this an advanced deployment rather than a one-command install on arbitrary hardware.
Download the complete repository using the current hf CLI:
bash
hf download BlackwellBoy/Boltbreaker-Nemotron-3.5-74B-A9B-NF4 --local-dir ./boltbreakerIn a compatible CUDA environment, run the supplied loader from its directory:
bash
cd boltbreakerpython load_bolt.py . --prompt "What is 17 * 19? Reply with only the integer."The loader uses CUDA device 0, reads saved NF4 metadata, verifies expected parameters and installs the model's cache/sparse-expert adapters. It loads repository Python code via trust_remote_code=True; review that code before running it. Keep all model shards and helper files together. Run programmatic inference inside torch.inference_mode().
The CLI smoke-test prompt is bounded to 128 tokens. The builder's separate HTTP wrapper was tested as a text-only, non-streaming service with a 4,096-token total limit and thinking off. Those are wrapper limits, not a newly established architectural context limit. Longer context and thinking-on quality were not validated for this derivative. Image support exists in the checkpoint; the evaluated HTTP wrapper did not accept images.
a6a1e5030819a130a1ea08aadb1fe42f4cc86777.c968a8bc4007efd72b24174c1d35bfd542caff75, with the included Bolt-specific adapter.SOURCE_README.md; its claims describe the upstream model, not validation of this derivative.License: OpenMDW 1.1. See LICENSE.OpenMDW-1.1 and retained upstream notices.
hf download BlackwellBoy/Boltbreaker-Nemotron-3.5-74B-A9B-NF4 --local-dir ./boltbreakercd boltbreakerpython load_bolt.py . --prompt "What is 17 * 19? Reply with only the integer."