size-local-model SKILL.md skillA
size-local-model from abhiindigloo/evalharness is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add abhiindigloo/evalharness/size-local-model@git:20261016.b34e048Pins git:20261016.b34e048 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- abhiindigloo/evalharness
- Path
skills/size-local-model/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261016.b34e048, committed Oct 16, 2026
- First version recorded
- Oct 14, 2026
- Size
- 3,433 bytes
- Repository stars
- 7
- License
- MIT
Estimate the GPU or unified memory needed to run an open-weight model locally, covering weights at a given precision or quantization plus KV cache for a chosen context length and concurrency, and compare it with available memory. Use whenever the user asks whether a model fits their GPU, Mac, or server, how much VRAM or RAM a model needs, what quantization to use, how context length or batch size affects memory, or how to size hardware for Ollama, llama.cpp, vLLM, or LM Studio, even if they…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Estimate local model memory
## Gather inputs from official sources
Read the model card or the model's `config.json` from its official repository. Do not guess architecture values.
| Input | Where it comes from |
|---|---|
| Total stored parameters (billions) | Model card. For mixture-of-experts models use **total** parameters, not active ones: all experts are loaded. |
| Effective bits per weight | 16 for BF16/FP16, 8 for 8-bit, about 4–5 for common 4-bit formats. Most accurate: `file size in bytes × 8 ÷ parameter count` from the actual download. |
| Layers | `num_hidden_layers` |
| KV heads | `num_key_value_heads`; if absent, the model uses standard multi-head attention, so use `num_attention_heads`. |
| Head dimension | `head_dim` if present, otherwise `hidden_size ÷ num_attention_heads`. |
| Context | Tokens the user plans to use per sequence, not the advertised maximum. |
| Concurrency | Sequences served at the same time (1 for a single user). |
| KV precision | 16 by default; 8 if the runtime is set to quantize the KV cache. |
## Run
```
python3 scripts/estimate_memory.py --params-b 8.03 --bits 16 \
--layers 32 --kv-heads 8 --head-dim 128 --context 8192 \
…Read the whole file at its exact version.
How to install
mdr add abhiindigloo/evalharness/size-local-model@sha256:a10378decd8a15f6The line at the top of this page pins the label git:20261016.b34e048, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_4622r2m53isvmxk7)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Oct 14, 2026 and Oct 16, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261016.b34e048 latest | 2026-10-16 | b34e048 | 3,433 B | A | view · diff |
| git:20261014.4490b68 | 2026-10-14 | 4490b68 | 3,349 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3433 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
abhiindigloo/evalharness · 7 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_4622r2m53isvmxk7 GET https://markdownregistry.com/api/v1/resolve?ref=abhiindigloo/evalharness/size-local-model GET https://markdownregistry.com/api/v1/blob/a10378decd8a15f65af666b942066c989acf8972ad068dadaf7de2d88db09c45
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.