Seed OSS 36B Base — Hardware Requirements & GPU Compatibility
Chat
Seed-OSS-36B-Base is ByteDance's 36-billion-parameter open-source base language model, a dense transformer using GQA attention, RMSNorm, and SwiGLU, designed as a foundation for long-context, reasoning, and agentic downstream use. It is a pretrained model, not instruction-tuned, though this particular checkpoint's pretraining mix includes synthetic instruction data (ByteDance separately released a Base-woSyn variant trained without it, for researchers who want a foundation model unaffected by synthetic instruction data). Despite training on only 12 trillion tokens, it scores competitively against larger open pretrained models on knowledge, reasoning, and math benchmarks. At 36B parameters it needs a multi-GPU workstation or heavy quantization to run locally. Context length is 524,288 tokens, trained natively rather than extended after the fact. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in August 2025 alongside the instruction-tuned Seed-OSS-36B-Instruct.
47.3K downloads
68 likesSpecifications
- Publisher
- ByteDance-Seed
- Family
- Seed-OSS
- Parameters
- 36.2B
- Architecture
- SeedOssForCausalLM
- Context Length
- 524,288 tokens
- Vocabulary Size
- 155,136
- Release Date
- 2025-08-20
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Seed OSS 36B Base Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 15.9 GB | 84.4 GB | 15.36 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 16.4 GB | 84.8 GB | 15.82 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 18.2 GB | 86.6 GB | 17.62 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 22.3 GB | 90.7 GB | 21.69 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 26.3 GB | 94.8 GB | 25.76 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 30.4 GB | 98.8 GB | 29.82 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 36.7 GB | 105.2 GB | 36.15 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Seed OSS 36B Base?
Q4_K_M · 22.3 GBSeed OSS 36B Base (Q4_K_M) requires 22.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 29+ GB is recommended. Using the full 524K context window can add up to 68.4 GB, bringing total usage to 90.7 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090.
All compatible consumer-level GPUs are running near their VRAM limit. You may also want to consider professional GPUs (e.g., NVIDIA A100, H100) which offer significantly more VRAM. For more headroom and better throughput, consider a multi-GPU configuration with tensor parallelism (supported by tools like vLLM, llama.cpp, or text-generation-inference).
Which Devices Can Run Seed OSS 36B Base?
Q4_K_M · 22.3 GB41 devices with unified memory can run Seed OSS 36B Base, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Seed OSS 36B Base
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does Seed OSS 36B Base need?
Seed OSS 36B Base requires 22.3 GB of VRAM at Q4_K_M, or 72.9 GB at BF16. Full 524K context adds up to 68.4 GB (90.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 36.2B × 4.8 bits ÷ 8 = 21.7 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 69 GB (at full 524K context)
VRAM usage by quantization
Q4_K_M22.3 GBQ4_K_M + full context90.7 GB- Can NVIDIA GeForce RTX 4090 run Seed OSS 36B Base?
Yes, at Q4_K_M (22.3 GB) or lower. Higher quantizations like Q5_K_S (25.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Seed OSS 36B Base?
For Seed OSS 36B Base, Q4_K_M (22.3 GB) offers the best balance of quality and VRAM usage. Q5_K_S (25.4 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 15.9 GB.
VRAM requirement by quantization
Q2_K15.9 GBQ3_K_L19.1 GBQ4_K_M ★22.3 GBQ5_K_S25.4 GBQ5_K_M26.3 GBBF1672.9 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Seed OSS 36B Base on a Mac?
Seed OSS 36B Base requires at least 15.9 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Seed OSS 36B Base locally?
Yes — Seed OSS 36B Base can run locally on consumer hardware. At Q4_K_M quantization it needs 22.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Seed OSS 36B Base?
At Q4_K_M, Seed OSS 36B Base can reach ~216 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~29 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 22.3 × 0.65 = ~234 tok/s
Estimated speed at Q4_K_M (22.3 GB)
~234 tok/s~29 tok/s~234 tok/s~216 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Seed OSS 36B Base?
At Q4_K_M, the download is about 21.69 GB. The full-precision BF16 version is 72.30 GB. The smallest option (Q2_K) is 15.36 GB.
- Which GPUs can run Seed OSS 36B Base?
7 consumer GPUs can run Seed OSS 36B Base at Q4_K_M (22.3 GB). Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
- Which devices can run Seed OSS 36B Base?
41 devices with unified memory can run Seed OSS 36B Base at Q4_K_M (22.3 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.