RLVR 8B 0926 is an open-source chat model from StepFun that takes and returns text. It is designed for parallel coordinated reasoning tasks, using a framework to explore multiple reasoning paths and synthesize the results.
Input
Output
Context
328K
Max Output
-
Parameters
8.2B
Input Modalities
Output Modalities
None the catalog can show from stated facts or measured scores.
Download 16.4 GB · Runs on vLLM v0.32.0 · 2 GGUF builds
| Precision | Weights | One request at 33K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 15.3 GB | 19.5 GB | 1x NVIDIA GeForce RTX 3090 (24 GB) |
| INT8 | 7.63 GB | 11.5 GB | 1x NVIDIA T4 (16 GB) |
| INT4 | 3.81 GB | 7.48 GB | 1x NVIDIA T4 (16 GB) |
Computed by Inferbase from the 8,190,735,360 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.
RLVR 8B 0926 has a context window of 327,680 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. RLVR 8B 0926 is an open-weight model under the MIT license. You can download and self-host it within the license terms.
RLVR 8B 0926 has 8,190,735,360 parameters (8.2B), as stated in the creator's Hugging Face repository.
Strengths: Open weights under a permissive license (mit); 327K token context window. Each is computed from the model's stated facts and benchmark results.
RLVR 8B 0926 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 RLVR 8B 0926 yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves RLVR 8B 0926, and Inferbase runs it on your account with the same routing and logs.
The weights take 15.3 GB at FP16 / BF16, 7.6 GB at INT8, 3.8 GB at INT4, computed from the 8,190,735,360 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.