ABLAGENT-35B-A3B-NVFP4

BLACKFROST PRO SERIES · BLACKWELL NVFP4 DEPLOYMENT EDITION

Controlled-access professional toolkit. This is the Blackwell-focused NVFP4 edition of ABLAGENT-35B-A3B-BF16, packaged with a bounded standalone harness for professional model-engineering workflows. It is not presented as a general chat assistant, autonomous weight-editing system, or production- readiness guarantee.

Release status and contents

This repository is public and manually gated; every access request requires Blackfrost Research approval. It contains a complete standalone compressed-tensors NVFP4 checkpoint—not an adapter—plus tokenizer and multimodal processor assets, artifact checksums, a validated language-only deployment kit, and Blackfrost Ablagent Standalone Harness 1.0.0.

Blackfrost Pro Series releases combine a task-specific model artifact, a defined operating boundary, a harness or integration surface, deployment guidance, and a measured validation record. Tools, data access, write authority, and promotion decisions remain explicitly operator-governed.

Why this release exists

ABLAGENT-35B-A3B-NVFP4 provides a compact native-Blackwell deployment representation derived directly from the canonical BF16 edition. It remains an Ablagent professional toolkit for inspecting artifacts, reconciling run evidence, comparing candidates, diagnosing incomplete experiments, and preparing clear operator handoffs.

Toolkit profile

The harness can inspect an explicitly authorized workspace through bounded read_file, grep, and glob tools. It does not expose a shell, modify weights, deploy services, publish artifacts, or write into the workspace. Missing evidence remains missing rather than being treated as a pass.

Model specifications

Architecture and context values are checkpoint specifications. Runtime capacity is backend and hardware dependent. Native NVFP4 execution requires a compatible backend and NVIDIA GPU. The included processor and vision payload were preserved, but multimodal quality was not re-benchmarked.

Complete lineage

1. Foundational checkpoint: openbmb/MiniCPM-V-4.7-35B-A3B, immutable revision 4c7623a9326e0f74313bbc7292d852a9e3018a70.
2. Blackfrost behaviorally modified derivative. The proprietary transformation process and its reconstruction materials are not distributed.
3. Canonical BF16 parent: Blackfrost-Research/ABLAGENT-35B-A3B-BF16, immutable revision 9304f7634ceb66ba6a9a83698cac7982932b1ed2.
4. Direct NVFP4 deployment conversion using LLM Compressor 0.14.1.dev35+gdcd820df at commit dcd820dfbad79b3191600f42278fc70e88c78e7b, compressed-tensors 0.19.1a20261013, Transformers 5.19.0, and PyTorch 2.12.0+cu130.

The final conversion stage did not apply another behavioral transformation. Tokenizer, chat template, and processor lineage comes from the pinned foundational checkpoint. The upstream and this release declare Apache License 2.0; see UPSTREAM-LICENSE-NOTICE.md.

Artifact verification and checksums

Verify the downloaded runtime files from the repository root:

sha256sum --check ARTIFACT-CHECKSUMS.sha256
sha256sum --check DEPLOYMENT/CHECKSUMS.sha256

Behavioral and capability evaluation

• The output index contains 124,432 tensors with no missing, misplaced, or duplicate entries.
• 92,640 quantization scale tensors passed finite-value validation; zero non-finite scales were found.
• The checkpoint loaded natively as compressed-tensors on one NVIDIA B300 at TP1 with a 262,144-token configured context.
• /v1/models returned exactly ABLAGENT-35B-A3B-NVFP4.
• A deterministic minimal generation returned the correct result for 19 × 37.
• The bundled harness passes 14 package, privacy, controller, and bounded-tool tests.
• These are conversion-integrity, structural, packaging, and liveness checks—not a comprehensive benchmark.
• No comprehensive multimodal, safety, long-context, or native tool-calling evaluation has been published for this derivative.

Prompt, template, and sampling notes

Use the included chat template and native OpenAI-compatible messages. The validated server enabled thinking and used the qwen3 reasoning parser plus the qwen3_coder tool-call parser. Keep reasoning_content separate from user-visible content and preserve the parser/template pairing.

The checkpoint generation configuration advertises temperature 1.0, top-k 20, and top-p 0.95. The minimal release smoke used temperature 0. Set sampling explicitly for every measured workload and provide enough output budget for both reasoning and the final response.

Deployment

DEPLOYMENT/ records the exact validated hardware class, runtime source commit, container content ID, TP setting, launch flags, context, API shape, and smoke test. The backend and GPU must support native compressed-tensors NVFP4. The launcher sets the clean API identity ABLAGENT-35B-A3B-NVFP4; the smoke test refuses any other identity.

HARNESS/ contains the same Blackfrost Ablagent Standalone Harness used by the other Ablagent releases. Configure and probe it only after the model endpoint passes the deployment-kit smoke test:

cp HARNESS/config.35b.example.json HARNESS/config.local.json
HARNESS/bin/ablagent --config HARNESS/config.local.json --probe

Read HARNESS/docs/SECURITY.md, HARNESS/docs/READINESS.md, and HARNESS/docs/SERVER.md before broader use.

Limitations, security, license, and disclaimer

• Native NVFP4 depends on backend and GPU support. Silent dequantization or fallback was not part of the validated path.
• The validated deployment path is language-only; it does not load the vision tower or multimodal projector.
• Configured 262K context is not a claim that every request length, concurrency level, or workload has been accepted.
• Quantization can change behavior relative to BF16; independently evaluate task quality.
• The model may refuse, comply incorrectly, hallucinate, or produce unsafe output. No claim of complete refusal removal, harmlessness, or production readiness is made.
• The current harness is a read-only evaluation surface, not a production automation controller.
• Operators are responsible for authorization, access control, prompt/data handling, tool permissions, output review, legal compliance, and independent evaluation.
• The checkpoint and bundled harness are provided under Apache License 2.0 with their respective notices. This is not a warranty of fitness for any purpose.

Do not redistribute access or mirror the gated weights without authorization. Report packaging, runtime, license, or security issues through this repository's Discussions tab without posting secrets, private prompts, or gated artifacts.

---

BLACKFROST PRO SERIES
Professional models. Defined workflows. Operator control.

ABLAGENT-35B-A3B-NVFP4 · © 2026 Blackfrost Softwares Corp.