Seed GGUF models

111 GGUF models in the Seed family, quantized by 49 uploaders. Sizes run from 124M to 36.2B parameters. The longest trained context is 512K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
SE
Hermes 4_3_36b
Seed · NousResearch
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningRoleplayTool use
SE
Seed-Oss-36B-Instruct
Seed · unsloth
Params36.2B
Context512K
Q4_K_M21.8 GB
GGUF
SE
Seed-Coder-8B-Reasoning
Seed · unsloth
Params8.25B
Context64K
Q4_K_M5.1 GB
CodingReasoning
SE
Seed OSS 36B Instruct Abliterated
Seed · mradermacher
Params36.2B
Context512K
Q4_K_M21.8 GB
GGUF
SE
Seed-Coder-8B-Instruct
Seed · unsloth
Params8.25B
Context32K
Q4_K_M5.1 GB
Coding
SE
Seed X PPO 7B
Seed · mradermacher
Params7.51B
Context32K
Q4_K_M4.6 GB
GGUF
SE
Seed OSS 36B Instruct
Seed · bartowski
Params36.2B
Context512K
Q4_K_M21.8 GB
GGUF
SE
ByteDance Seed_Seed OSS 36B Instruct
Seed · lmstudio-community
Params36.2B
Context512K
Q4_K_M21.8 GB
GGUF
SE
Seed Coder 8B Instruct
Seed · mradermacher
Params8.25B
Context32K
Q4_K_M5.1 GB
Coding
SE
Seed OSS 36B Base
Seed · mradermacher
Params36.2B
Context512K
Q4_K_M21.8 GB
GGUF
SE
Seed Coder 8B Instruct
Seed · mradermacher
Params8.25B
Context32K
Q4_K_M5.1 GB
Coding
SE
Seed Coder 8B Reasoning
Seed · mradermacher
Params8.25B
Context64K
Q4_K_M5.1 GB
CodingReasoning
SE
Seed Coder 8B Base
Seed · mradermacher
Params8.25B
Context32K
Q4_K_M5.1 GB
Coding
SE
Seed Coder 8B Instruct
Seed · second-state
Params8.25B
Context32K
Q4_K_M5.1 GB
Coding
SE
Seed X Instruct 7B
Seed · mradermacher
Params7.51B
Context32K
Q4_K_M4.6 GB
GGUF
SE
Seed X PPO 7B
Seed · Sangto
Params7.51B
Context32K
Smallest8.0 GB
GGUF
SE
Seed Coder 8B Instruct Rust Strandset
Seed · snsnc
Params8.25B
Context32K
Q4_K_M5.1 GB
Coding
SE
Seed OSS 36B Base Instruct Karcher Merge
Seed · mradermacher
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningTool use
SE
Seed OSS 36B Instruct Biprojected Norm Preserving Abliterated
Seed · mradermacher
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningTool use
SE
Seed Coder 8B Instruct
Seed · gaianet
Params8.25B
Context32K
Q4_K_M5.1 GB
Coding
SE
Seed OSS 36B Instruct Abliterated
Seed · mradermacher
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningTool use
SE
Seed OSS 36B Instruct
Seed · mradermacher
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningTool use
SE
Seed OSS 36B Base woSyn
Seed · mradermacher
Params36.2B
Context512K
Q4_K_M21.8 GB
GGUF
SE
Seed-Coder-8B-Reasoning
Seed · Mungert
Params8.25B
Context64K
Q4_K_M5.2 GB
CodingReasoning
SE
Seed OSS 36B Instruct
Seed · second-state
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningTool use
SE
Seed Coder 8B Reasoning
Seed · second-state
Params8.25B
Context64K
Q4_K_M5.1 GB
CodingReasoning
SE
Seed OSS 36B Instruct MPOA v1
Seed · mradermacher
Params36.2B
Context512K
Q4_K_M21.8 GB
GGUF
SE
Seed OSS 36B Instruct
Seed · RDson
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningTool use
SE
Seed OSS 36B Instruct
Seed · gabriellarson
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningTool use
SE
Seed OSS 36B Instruct Biprojected Norm Preserving Abliterated
Seed · mradermacher
Params36.2B
Context512K
Q4_K_M21.8 GB
ReasoningTool use

About the Seed GGUF models

Seed is represented on ggufmodels.com by 111 GGUF models, quantized by 49 uploaders on Hugging Face. The most downloaded are Hermes 4_3_36b, Seed-Oss-36B-Instruct and Seed-Coder-8B-Reasoning. Parameter counts run from 124M to 36.2B, and the longest trained context window is 512K tokens.

A Q4_K_M file of a Seed model is between 0.1 to 21.8 GB, which is the quant most people start with. Most files come from mradermacher (32), DevQuasar (8) and tensorblock (7). The quants you will meet most often are Q4_K_M (85), Q2_K (70), Q6_K (68) and Q5_K_M (66), where the number is how many models offer that quant.

Frequently asked questions

Which Seed GGUF should I download?

The most downloaded Seed GGUF here is Hermes 4_3_36b. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Seed model need?

Q4_K_M files of Seed models on this site range from 0.1 to 21.8 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Seed GGUF files come from?

The most common quantizers here are mradermacher, DevQuasar and tensorblock. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing