RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Methodology

Every number on RunsOnMy is computed by one small, deterministic JavaScript module that runs the same way at build time, in the Worker and in your browser. Nothing is written by hand per model.

Total memory

total = weights + KV cache + overhead

Weights

When a GGUF build exists on Hugging Face (from the model maker, Unsloth, bartowski, LM Studio Community or ggml-org) we use the real file size of each quant, summing split files. Otherwise we estimate parameters × bits-per-weight ÷ 8 with llama.cpp's average bits per weight:

QuantBits per weightQuality
Q2_K3rough
Q3_K_M3.91usable
Q4_K_M4.89good, most popular
Q5_K_M5.7very good
Q6_K6.56near lossless
Q8_08.5effectively lossless
F1616original weights

Parameter counts come from the safetensors metadata on Hugging Face. For mixture-of-experts models, all experts must be in memory, so memory uses total parameters. Active parameters (used for speed) are computed from the config: total − MoE layers × (experts − experts per token) × 3 × hidden × expert FFN size.

KV cache

Pages for models with newer compressed-attention designs we can't model exactly are labeled as upper bounds.

Overhead

0.4 GiB + vocabulary size × 512 × 4 bytes, covering the runtime context and the logits/compute buffer at the default 512-token batch.

Usable memory

Fits = total ≤ 90% of usable memory. Tight = 90–100%. No = over.

Speed ceiling

Generating one token reads all active weights once, so tokens/sec ≤ memory bandwidth ÷ (weights × active/total parameters). This is an upper bound; real llama.cpp speeds are usually 50–80% of it. We label it an estimate everywhere and will replace it with measured, opt-in benchmark results.

Runs with offload (slower)

When a model does not fit in a discrete GPU's VRAM, llama.cpp can keep part of it in system RAM. Fit pages then show a Runs with offload result with the exact command and an estimated speed range. Every offload figure is an estimate, not a benchmark.

How the estimate compares with published llama.cpp results

The 0.45–0.5 RAM efficiency was calibrated on these public runs. Our N is the value our formula picks; theirs is what the tester used.

Model, hardwareTheir NMeasuredOur NOur estimateSource
gpt-oss-120b, RTX 3090 24 GB, DDR5-5200--n-cpu-moe 2526.9 tok/s2417–34llama.cpp gpt-oss guide, comment Jan 20 2026
gpt-oss-120b, RTX 5090 32 GB--n-cpu-moe 21~30 tok/s1922–44llama.cpp gpt-oss guide (ggml-org)
gpt-oss-120b, RTX 4060 Laptop 8 GB, DDR5-5200--n-cpu-moe 3418.9 tok/s3312–23 (desktop 4060)llama.cpp gpt-oss guide, comment Nov 10 2025
gpt-oss-20b, RTX 4060 Laptop 8 GB, DDR5-5200--n-cpu-moe 1442.3 tok/s1227–44 (desktop 4060)same comment
gpt-oss-120b, RTX 4070 12 GB, DDR5-6000-ngl 37 + tensor overrides23.9 tok/s3113–26carteakey.dev
Llama 7B Q4_0 (dense), CUDA GPU, hardware not stated-ngl 10 / 20 of 3313.5 / 21.4 tok/s—8.5–17.5 / 14.5–28.6llama-bench README

Measured numbers are single-user decode speed (llama-bench tg128 or llama-server). Our estimates use the model's Q4_K_M GGUF size at 8K context; the testers mostly used MXFP4 files of nearly the same size. We found no primary benchmark for 70B-class dense models with partial offload, so those estimates (about 1–2 tok/s on a 24 GB card) rest on the formula alone. Ranges are wide on purpose: RAM speed changes offload speed about 3× (DDR5 at 2000 vs 6000 MT/s).

What fits instead

Fit pages list the cheapest listed GPU that runs the model fully in VRAM at 8K context (by US launch MSRP from the vendor's announcement; street prices differ, and Macs and data-center cards have no list price here) and the largest popular model that fits the card at 4-bit or better (popular = the 60 most-downloaded models we track).

GPU specs. Memory, bandwidth and launch MSRP come from NVIDIA, AMD, Intel and Apple product pages and launch announcements, last re-checked Nov 17, 2026. NVIDIA no longer lists bandwidth for RTX 30 and 40 series cards on its comparison page, only bus width and memory speed; for those cards the bandwidth is bus width × data rate, matching NVIDIA's launch materials where they state it.

API prices

Prices come from OpenRouter's public models API every 6 hours. Each snapshot is compared to the previous one and every change is logged (change log). Where LiteLLM's MIT-licensed price map has the model maker's own entry, we show it side by side and flag differences.

Automated accuracy checks

Before every build, a check script runs golden tests against reference values computed independently from the models' published configs and sanity gates on every page. A model page is held back (not published) if its numbers fail, for example missing architecture or memory below the file size. GGUF sizes that disagree with the parameter count are discarded in favour of estimates. A model is also held when the size in its name (for example "27B", "8x7B" or "17B-16E") is more than 1.8× away from both its total and active parameter counts, which usually means a draft head or broken metadata. Speculative-decoding draft models (DSpine, DFlash, EAGLE, Medusa, MTP heads) are left out of the catalog because their parameter count is the small draft, not the model in the name. The build is blocked if the golden tests fail or more than 20% of pages are held.

Latest run: Nov 18, 2026 · 298 models checked, 0 held · golden tests: 3/3 passed · 147 prices cross-checked with LiteLLM, 30 differ.

What we don't model

Refresh schedule

Spotted something wrong? Tell us. Confirmed fixes are listed on the corrections log.