AI ERP with agents inside the systems you run
AI phone and voice agents for real calls
LLM.coPrivate, self-hosted LLM deployments
Legal AI infrastructure for firms
AI RFP discovery and response drafting
Automatic.coBusiness process automation
CyberAttack.aiThreat detection and defense
Secure AI virtual data roomsSeed-OSS-36B-Instruct
Seed-OSS-36B-Instruct is a 36-billion-parameter open-source language model from ByteDance's Seed Team, released under Apache-2.0. It supports 512K context length natively and is optimized for reasoning, agent tasks, and long-context scenarios. The model achieves competitive performance on standard benchmarks (MMLU-Pro: 82.7%, MATH: 81.7% base version) despite being trained on only 12T tokens. No gating required; available for immediate download.
Key facts
Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.
| Field | Value |
|---|---|
| Developer | ByteDance-Seed |
| Parameters | 36.2B |
| Context window | Unknown |
| License | apache-2.0 — OSI-approved |
| Modality / task | text-generation |
| Gated on HuggingFace | No |
| Downloads | 37.5k |
| Likes | 503 |
| Last updated | 2025-08-26 |
| Source | ByteDance-Seed/Seed-OSS-36B-Instruct |
What Seed-OSS-36B-Instruct is
Causal language model with GQA attention, SwiGLU activation, RMSNorm, and RoPE positional encoding. Architecture: 64 layers, 80 QKV heads with 8 KV heads, 5120 hidden size, 128 head size, 155K vocabulary. Trained with up to 512K context natively. Two variants available: with and without synthetic instruction data in pretraining. Last update: 2025-08-26.
Run Seed-OSS-36B-Instruct locally
Load the open weights with 🤗 Transformers and generate — the same model, self-hosted.
from transformers import pipelinepipe = pipeline("text-generation", model="ByteDance-Seed/Seed-OSS-36B-Instruct")out = pipe("Explain retrieval-augmented generation in one sentence.", max_new_tokens=128)print(out[0]["generated_text"])Swap in vLLM or Ollama for production-grade serving. DEV.co can stand up the inference stack.
How you'd run it
A typical self-hosted path — open weights, an inference server, your application.
DEV.co builds each layer — from GPU infrastructure to the application.
Best use cases
Running & fine-tuning it
ESTIMATE: 36B parameters in bfloat16 = ~72 GB VRAM. Full precision (float32) ≈ 144 GB. Feasible on single high-end GPU (H100 80GB would require quantization or pipeline parallelism) or multi-GPU setup. For inference optimization: quantization (int8/int4) could reduce to 18–36 GB. Serving frameworks like vLLM support distributed inference. Exact throughput metrics not provided; requires testing.
Model card does not explicitly document LoRA/QLoRA feasibility, adapters, or fine-tuning guidelines. Standard HuggingFace transformers library compatibility assumed (architecture uses standard components: RoPE, GQA, SwiGLU). LoRA fine-tuning likely feasible but requires empirical validation. Two base variants (with/without synthetic data) available for research-oriented fine-tuning, offering flexibility for downstream task adaptation.
When to avoid it — and what to weigh
- Production systems requiring guaranteed latency SLAs — 36B parameter model will require substantial compute. Inference latency and throughput depend heavily on hardware and serving framework. No benchmarked serving metrics provided.
- Strict real-time knowledge cutoff or fact-heavy QA — SimpleQA performance is low (9.7% on instruct variant). Model may not be optimal for applications requiring up-to-date factual accuracy without retrieval augmentation.
- Resource-constrained edge or mobile deployment — 36B parameters require significant GPU/TPU memory. Quantization or distillation would be necessary for edge devices; no pre-quantized variants mentioned.
- Closed commercial environments with strict provenance requirements — Synthetic instruction data used in training may not meet some enterprise audit requirements. Model card offers non-synthetic variant (Seed-OSS-36B-Base-woSyn) but instruct variant uses synthetic data.
License & commercial use
Apache-2.0 license. Permissive open-source license (OSI-approved) granting rights to use, modify, and distribute subject to license notice and disclaimer retention.
Apache-2.0 is a permissive OSI license that explicitly permits commercial use, modification, and distribution, provided license conditions are met (retain license notices, state material changes, include disclaimer). No additional commercial restrictions in model card. However, verify with legal counsel whether synthetic instruction data in pretraining triggers any third-party licensing obligations not disclosed here. Non-synthetic base variant (Seed-OSS-36B-Base-woSyn) available if provenance sensitivity exists.
DEV.co evaluation signals
Editorial assessment — not user reviews. Directional, with an explicit confidence level.
| Signal | Assessment |
|---|---|
| Maintenance | Active |
| Documentation | Adequate |
| License clarity | Clear |
| Deployment complexity | Moderate |
| DEV.co fit | Strong |
| Assessment confidence | High |
No formal security audit, penetration testing, or adversarial robustness evaluation mentioned. Standard LLM risks apply: model poisoning via synthetic data, prompt injection, information leakage in long contexts, and misuse for automated harmful content generation. Synthetic instruction data used in base model introduces potential alignment inconsistencies compared to human-authored data. No stated content filtering or safety fine-tuning. Recommend: (1) pre-deployment adversarial testing, (2) input validation/filtering in production, (3) monitoring for jailbreak attempts, (4) data governance for sensitive use cases (healthcare, finance).
Alternatives to consider
Qwen2.5-32B or Qwen3-32B
Similar parameter count and competitive MMLU-Pro performance (58.5–81.8 depending on variant). Qwen ecosystem offers more serving tooling and community examples. Seed-OSS-36B outperforms on MATH (81.7 vs. 63.5) but trails on SimpleQA (9.7 vs. 6.1–8.6).
Gemma3-27B
27B alternative with comparable reasoning capability (BBH, math benchmarks). Smaller footprint reduces hardware requirements. Lower MMLU-Pro (67.5) and coding performance but may suit edge-constrained scenarios.
OAI-OSS-20B (Open-Source GPT-4-class models, if available)
Smaller footprint (20B) with competitive instruct-mode MMLU-Pro (76.2%) and superior AIME performance (92.7%). Trade-off: smaller model size vs. Seed-OSS-36B's long-context strength (512K).
Ship Seed-OSS-36B-Instruct with senior software developers
Start with a benchmark on your hardware, evaluate on your domain tasks, and consider quantization for cost optimization. For agent-heavy or long-context workloads, test against Qwen and OAI-OSS alternatives. Consult our team for production-scale serving architecture.
Talk to DEV.coRelated open-source tools
Surfaced by semantic similarity across the DEV.co open-source index.
Related on DEV.co
Explore the category and the services that help you build with it.
Seed-OSS-36B-Instruct FAQ
Can I use this model commercially?
What GPU do I need to run this model?
How does Seed-OSS-36B compare to closed models like GPT-4?
Are there pre-trained vs. instruction-tuned variants?
Custom software development, end to end
DEV.co has shipped open-source llms software across regulated and high-growth industries. Our software development services and AI development services cover the work that follows a decision to adopt Seed-OSS-36B-Instruct.
Ready to Deploy Seed-OSS-36B?
Start with a benchmark on your hardware, evaluate on your domain tasks, and consider quantization for cost optimization. For agent-heavy or long-context workloads, test against Qwen and OAI-OSS alternatives. Consult our team for production-scale serving architecture.