Seed X RM 7B is an open-source reward model created by ByteDance for evaluating multilingual translations. It is a causal language model trained on human preference data to assess translations between numerous languages.
Input
Output
Context
33K
Max Output
512
Parameters
7.2B
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
None the catalog can show from stated facts or measured scores.
Download 14.5 GB · Runs on vLLM v0.32.0 · 1 GGUF builds
| Precision | Weights | One request at 33K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 13.5 GB | 17.6 GB | 1x NVIDIA GeForce RTX 3090 (24 GB) |
| INT8 | 6.75 GB | 10.6 GB | 1x NVIDIA T4 (16 GB) |
| INT4 | 3.37 GB | 7.01 GB | 1x NVIDIA T4 (16 GB) |
Computed by Inferbase from the 7,246,946,304 parameters in the creator's Hugging Face repository; one request adds its KV cache, activations and framework overhead, with the layer layout estimated from the parameter count.
Public resources
Specification sources
As of Nov 10, 2026.
Answered from the facts on this page, with their sources.
Seed X RM 7B has a context window of 32,768 tokens and a maximum output of 512 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. Seed X RM 7B is an open-weight model under the Other license. You can download and self-host it within the license terms.
Seed X RM 7B has 7,246,946,304 parameters (7.2B), as stated in the creator's Hugging Face repository.
Seed X RM 7B accepts Text and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for Seed X RM 7B yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves Seed X RM 7B, and Inferbase runs it on your account with the same routing and logs.
The weights take 13.5 GB at FP16 / BF16, 6.7 GB at INT8, 3.4 GB at INT4, computed from the 7,246,946,304 parameters its creator publishes. Each request adds its KV cache and the framework's overhead. The hardware section shows one request and the smallest GPU that fits; the GPU planner sizes it for your context length and traffic.
Start on the free plan with 5,000 requests a month, no card required.