ABLAGENT-35B-A3B-BF16

BLACKFROST PRO SERIES · PROFESSIONAL MODEL ENGINEERING TOOLKIT

Controlled-access professional toolkit. ABLAGENT-35B-A3B-BF16 packages a complete high-precision checkpoint, a bounded standalone harness, and a validated deployment path 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 the complete standalone BF16 checkpoint, 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-BF16 is the canonical high-precision artifact for this Ablagent 35B-A3B family and the direct parent of its FP8 and NVFP4 deployment editions. It is packaged as a professional assistant for the work around controlled model-modification programs: inspecting artifacts, reconciling run evidence, comparing candidates, diagnosing incomplete experiments, and producing 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. The included processor and vision payload were preserved, but multimodal quality was not re-benchmarked for this release.

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. BF16 packaging, structural verification, and validated SGLang deployment as ABLAGENT-35B-A3B-BF16. This packaging 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

• Exact source/output tensor inventory checks passed before publication.
• The checkpoint loaded on one NVIDIA B300 at TP1 with a 262,144-token configured context.
• /v1/models returned exactly ABLAGENT-35B-A3B-BF16.
• 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 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 launcher sets the clean API identity ABLAGENT-35B-A3B-BF16; 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

• 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.
• 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-BF16 · © 2026 Blackfrost Softwares Corp.