ModelVRAM
No liveness check has reached it yet; it is registered on GitHub and has been in the index since 14 Oct 2026. How this is checked
ModelVRAM is a web calculator for estimating the VRAM, tokens per second, and hardware compatibility of language models. It uses model configurations and weight files from Hugging Face to compare quantization formats, GPU and Mac setups, and MoE offload options for AI developers.
Inferred · not functionally tested
Overview
6 featuresPurpose: Choosing suitable hardware and quantization settings for running or fine-tuning large language models.
Inferred · not functionally tested
Audience: AI developers and machine learning engineers
Inferred · not functionally tested
Functions: analytics
Inferred · not functionally tested
Interfaces: API: unknown · MCP: unknown · CLI: unknown · Self-hosting: unknown
Recorded constraints: pricing: free · license: MIT · platforms: WEB · deployment: browser, cloud_managed
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: modelvram.com · github.com. These links do not verify the individual claims.
In the Other data science & ML space, ModelVRAM takes a focused approach. Inferred · not functionally tested: It focuses on choosing suitable hardware and quantization settings for running or fine-tuning large language models. Inferred · not functionally tested: It is built as a B2B product for AI developers and machine learning engineers. Basis unknown · not verified: It is available for free. Basis unknown · not verified: It runs on the web.
ModelVRAM first shipped in 2026. Development happens publicly on GitHub with 32 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are VRAM estimation, GPU matching, and mac setup matching. The interface is available in English and Chinese.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- VRAM estimation
- GPU matching
- Mac setup matching
- Token speed estimates
- Quantization comparison
- MoE offload splits
Topics: Inferred · not functionally tested
Built with & integrations
- Astro
- /_astro/ in the HTML
- local_oss
- bollama in the HTML · bllama in the HTML · bvllm in the HTML
- Cloudflare
- cf-ray header · cf-cache-status header
- meta_llama
- llama- in the HTML
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
Frequently asked questions about ModelVRAM
- What is ModelVRAM?
- Inferred · not functionally tested: ModelVRAM focuses on choosing suitable hardware and quantization settings for running or fine-tuning large language models. It is catalogued under Other data science & ML on PulseGate.
- Who should use ModelVRAM?
- Inferred · not functionally tested: ModelVRAM is a B2B product built for AI developers and machine learning engineers.
- Does ModelVRAM have a free plan?
- Basis unknown · not verified: Yes — ModelVRAM is free to use.
- What platforms does ModelVRAM run on?
- Basis unknown · not verified: ModelVRAM runs on the web.
- Is ModelVRAM still maintained?
- The GitHub repository shows 32 commits in the last 90 days.
- What projects are similar to ModelVRAM?
- Similar projects tracked by PulseGate include LLM Model VRAM Calculator, ModelFit, and Show HN: VRAM calculator that counts the text encoder, not just the weights.LLM Model VRAM CalculatorModelFitShow HN: VRAM calculator that counts the text encoder, not just the weights
- When did ModelVRAM launch?
- ModelVRAM first shipped in 2026.
- Is ModelVRAM open source?
- Basis unknown · not verified: ModelVRAM has a public GitHub repository.
Similar projects
Closest matches by what these projects do