Seed OSS 36B Instruct — Hardware Requirements & GPU Compatibility
ChatFunctions
Seed OSS 36B Instruct is a 36.2B-parameter open language model from ByteDance-Seed in the Seed-OSS family. It supports a context window of up to 524,288 tokens. At Q4_K_M it needs about 22.26 GB of VRAM — see which GPUs and Macs can run it below.
Decent on a 24 GB GPU
Runs from 16 GB (IQ2_M · 16K)Best on 24 GB (Q4_K_M · ~29 tok/s · 8K)Macs from 16 GB (IQ2_XXS · ~13 tok/s)
Score 102.5#46 of 100 open#8 of 35 that fit 24 GBApache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
llmrun Composite Score →
102.5
- 90% range 98.3–106.7
- #46 of 100 open models
- #8 of 35 that fit 24 GB
Run Seed OSS 36B Instruct
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/unsloth/Seed-OSS-36B-Instruct-GGUF:Q4_K_MQ4_K_M needs offload on the RTX 4090 · 0.1 GB short · 16K context
Download: Seed-OSS-36B-Instruct-Q4_K_M.gguf21.76 GBunsloth
Other ways
each opens step-by-stepRun in cloud
Fits on RTX PRO 4500 (32 GB) (7 GB headroom) · Q4_K_M
- Generation speed
- ~26 tok/s
- generation speed
- Cost per 1M output tokens
- $3.60
- per 1M output tokens
How Much VRAM Does Seed OSS 36B Instruct Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 15.9 GB | 20 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~41 tok/s | |
| 16.4 GB | 20.4 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~40 tok/s | |
| 18.2 GB | 22.2 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~36 tok/s | |
| 18.6 GB | 22.7 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~35 tok/s | |
| 22.3 GB | 26.3 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 8K context · ~29 tok/s | |
| 26.3 GB | 30.4 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Does not fit: needs 28.2 GB | |
| 30.4 GB | 34.4 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 32.3 GB | |
| 36.7 GB | 40.8 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 38.6 GB |
Selected Q4_K_M
4-bit medium quantization24.1GBat 16K context
- Weights
- 21.7 GB
- KV cache
- 2.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · fits up to 8K context · ~29 tok/s
≥50 tok/s needs ≥1.71 TB/s · RTX 5090 ~52
Which Hardware Can Run Seed OSS 36B Instruct?
Q4_K_M · 22.3 GBSeed OSS 36B Instruct (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. 100 devices with unified memory can run Seed OSS 36B Instruct, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M5 Max (36 GB).
20 GB
Q4_K_M · best fit IQ3_M (18.7 GB)
1 GPU
RX 7900 XT~29Simulate output on RX 7900 XT32–40 GB
fits · 7.9 GB free · up to 64K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~52Simulate output on RTX 5090M5 Max36 GB~15Simulate output on Mac Studio M5 Max (36 GB)M532 GB~5Simulate output on MacBook Air 13" M5 (32 GB)Orin~6Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~4Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is Seed OSS 36B Instruct?
The llmrun Score merges 3 public benchmark boards into a single figure, where 100 represents the average for open models.
Score vs VRAM in the 24 GB tier
- Seed OSS 36B Instruct
- Other models
- Best Score for its VRAM
#8 of 35 that fit 24 GB
Each dot is a model at the best quant that fits a 24 GB GPU. The line joins the models with the best Score for their VRAM; a dot below it is beaten by a model that needs no more memory.
Full 24 GB ranking →Benchmarks
Here are all 3 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
- GPQA Diamond
Epoch AI · Aug 2025Independent
Independent71.5%
#31/98 open
- AIME 2024/2025
Epoch AI · Aug 2025Independent
Independent67.5%
#30/86 open
- MMLU-Pro
TIGER-LabIndependent
Independent82.7%
#15/145 open
In the 24 GB class
35 models fit 24 GBSame Score, only models that fit 24 GB at their best quant: the ranking a 24 GB owner actually chooses from.
- #1
Qwen3.8 27BAlibaba
122.1
~38 tok/s · 17.9 GB
- #2
Qwen3.6 27BAlibaba
111.2
~38 tok/s · 17.9 GB
- #3
Gemma 4 31B ITGoogle
106.8
~32 tok/s · 21.7 GB
- #4
Qwen3.6 35B A3BAlibaba
106.8
~151 tok/s · 22.0 GB
- #5
Gemma 4 26B A4B ITGoogle
105.8
~171 tok/s · 16.5 GB
- #6
Qwen3.5 35B A3BAlibaba
105.8
~151 tok/s · 22.0 GB
Official models with an llmrun Score, each answering one question; numbers are at the best quant that fits a 24 GB GPU.
Best alternative at this size
Qwen3.8 27B
Alibaba
- 19.6 higher Score
- 4.9 GB less VRAM
- 6 tok/s faster
Score 122.1 · 17.9 GB · ~38 tok/s
Much faster, similar quality
Qwen3.6 35B A3B
Alibaba
- 4.3 higher Score
- 0.7 GB less VRAM
- 120 tok/s faster
Score 106.8 · 22 GB · ~151 tok/s
Fits in less VRAM
GPT OSS 20B
OpenAI
- 6.2 lower Score
- 9.6 GB less VRAM
- 158 tok/s faster
Score 96.3 · 13.1 GB · ~190 tok/s
Other vendor
Qwen3.6 27B
Alibaba
- 8.7 higher Score
- 4.9 GB less VRAM
- 6 tok/s faster
Score 111.2 · 17.9 GB · ~38 tok/s
Similar models
10| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Gemma 4 31B ITGoogle | 106.8 | 21.7 GB | ~32 | similar score |
| Gemma 4 26B A4B ITGoogle | 105.8 | 16.5 GB | ~171 | similar score |
| Qwen3.5 35B A3BAlibaba | 105.8 | 22 GB | ~151 | similar score |
| Qwen3.5 27BAlibaba | 103.8 | 17.9 GB | ~38 | similar score |
| Qwen3 30B A3B Thinking 2507Alibaba | 100.7 | 19.4 GB | ~173 | similar score |
| Qwen3.5 9BAlibaba | 99.4 | 6.6 GB | ~103 | similar score |
| Qwen3 32BAlibaba | 98.6 | 22.6 GB | ~32 | similar score |
| Qwen3 14BAlibaba | 98.0 | 11.9 GB | ~69 | similar score |
| Qwen3 8BAlibaba | 93.9 | 7.6 GB | ~119 | similar score |
| DeepSeek R1 Distill Qwen 32BDeepSeek | 97.2 | 23 GB | ~34 | same size |
Specifications
- 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
Frequently Asked Questions
How much VRAM does Seed OSS 36B Instruct need?
Seed OSS 36B Instruct 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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 69 GB (at full 524K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 4090 run Seed OSS 36B Instruct?
Yes, at Q5_0 (23.2 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 Instruct?
For Seed OSS 36B Instruct, Q4_K_M (22.3 GB) offers the best balance of quality and VRAM usage. Q4_K_L (22.7 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 10.5 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Seed OSS 36B Instruct on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Seed OSS 36B Instruct, the smallest at IQ2_XXS. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 22.3 GB of usable unified memory (RAM minus macOS overhead), from Mac Studio M1 Max (32 GB).
Can I run Seed OSS 36B Instruct locally?
Yes — Seed OSS 36B Instruct can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Seed OSS 36B Instruct?
At Q4_K_M, Seed OSS 36B Instruct 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 ÷ 22.26 × 0.65 = ~234 tok/s
Estimated speed at Q4_K_M (22.3 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Seed OSS 36B Instruct?
At Q4_K_M, the download is about 21.69 GB. The full-precision BF16 version is 72.30 GB. The smallest option (IQ2_XXS) is 9.94 GB.
Which GPUs can run Seed OSS 36B Instruct?
7 consumer GPUs can run Seed OSS 36B Instruct at Q4_K_M. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090.
Which devices can run Seed OSS 36B Instruct?
100 devices with unified memory can run Seed OSS 36B Instruct at Q4_K_M (22.3 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.