Seed-OSS 36B Instruct on AMD Radeon PRO W7800 32GB

Can the AMD Radeon PRO W7800 32GB run Seed-OSS 36B Instruct?

Yes, it runs well

Runs well. At Q4_K_M it needs about 26.4 GB of 32.0 GB usable, with an estimated speed of 16.8 tok/s.

Best quant: Q4_K_M
Generation speed: 16.8 tok/s
Prompt processing: 1,550 tok/s
First token (1K prompt): 0.7 s
Largest safe context: 28K

Best app to run it on the AMD Radeon PRO W7800 32GB

On Windows

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

lemonade pull unsloth/Seed-OSS-36B-Instruct-GGUF:Q4_K_M

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

On Linux

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

lemonade pull unsloth/Seed-OSS-36B-Instruct-GGUF:Q4_K_M

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

Want an agent? Seed-OSS 36B Instruct supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Seed-OSS 36B Instruct

Recommended for the AMD Radeon PRO W7800 32GB: Q4_K_M. Every other quantization has its own download link in the table below.

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q4_K_M file (opens in a new tab)

huggingface.co/unsloth/Seed-OSS-36B-Instruct-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Seed-OSS-36B-Instruct-GGUF:Q4_K_M

Original weights · Hugging Face

Full-precision files from ByteDance, for fine-tuning, vLLM, Transformers.

huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from ByteDance. The weights themselves download from Hugging Face.

github.com/ByteDance-Seed/seed-oss (opens in a new tab)

git clone https://github.com/ByteDance-Seed/seed-oss

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q4_K_M, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs well: How well it runs on the AMD Radeon PRO W7800 32GB: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	34.2 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	9.7 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	83.9 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the AMD Radeon PRO W7800 32GB

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	18.8 GB	32.0 GB	27.7 tok/s	Runs well	56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	22.1 GB	32.0 GB	21.8 tok/s	Runs well	67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	26.4 GB	32.0 GB	16.8 tok/s	Runs well	76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	30.0 GB	32.0 GB	13.9 tok/s	Runs welltight fit	77Great quality (A) · 77 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	34.0 GB	32.0 GB	8.2 tok/s	Slowoffloads to RAM	79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	42.7 GB	32.0 GB	3.1 tok/s	Slowoffloads to RAM	80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	76.6 GB	32.0 GB	—	Won't run	80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q4_K_M · 60.9 tok/s · Runs great
79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q6_K · 42.2 tok/s · Runs great
67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q3_K_M · 41.1 tok/s · Runs well (tight fit)
67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q3_K_M · 44.2 tok/s · Runs well (tight fit)
67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q3_K_M · 36.3 tok/s · Runs well (tight fit)
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q4_K_M · 16.0 tok/s · Runs well

Quick answers

How much memory does Seed-OSS 36B Instruct need on the PRO W7800 32GB?

At Q4_K_M it needs about 26.4 GB. The PRO W7800 32GB has 32.0 GB usable.

How fast is Seed-OSS 36B Instruct on the PRO W7800 32GB?

About 16.8 tok/s at Q4_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Seed-OSS 36B Instruct should I use on the PRO W7800 32GB?

Q4_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.