FitMyLLM
498 models · 1,720 GPUs · updated daily

Find the best AI model for your computer.

Tell us your GPU and we rank 498 models by real speed, memory fit and quality, then give you the command to run the best one. About two seconds, no signup.

  • Runs in your browser
  • No account
  • No lock-in
Top picks for chat
Q4_K_M · 4K context
VRAM 24 GBBandwidth 1008 GB/s
Modeltok/sVRAMScore
1Qwen3.5-27B4819.670
2Qwen 3.5 9B7613.267
3Qwen 3.5 35B A3B23520.565
$

Computed by the same engine as the Match. Pick a GPU to stop the rotation.

0
Models ranked
Text, vision and embedding
0
GPUs in the catalogue
NVIDIA, AMD, Apple, Intel
0
CPUs for offload
Intel, AMD, Apple Silicon
From our lab

Measured, not estimated.

We rent the cards people actually buy, load every model that fits, and time it with the same harness each time. These are real decode speeds, not numbers worked out from a spec sheet.

Read the rig reports → · 6 consumer cards, each with every model timed.

Qwen3 30B A3Bdecode tok/s · Q4_K_M · 4K context
doesn't fit · 12 GBno fit
doesn't fit · 12 GBno fit
doesn't fit · 16 GBno fit
208 tok/s
259 tok/s
353 tok/s
llama.cpp, one card, same harness on each. Measured 2026-07 to 2026-08.

Four ways in

Pick the one that sounds like you. You can switch any time.

The weekly briefing.

New models · GPU deals · benchmark updates. Once a week. Unsubscribe with one click.

No spam · No trackers · Powered by Buttondown

PlusEvery result instead of the first, filters, 4-way compare and all the measured rig reports.$4.99/month →

QuickStart

Pick your GPU and get the best model for it, with the command to run it.

Probing hardware
Reading WebGL renderer, matching against 0 GPU database…

Run AI Locally on Your Computer — No Cloud, No Subscriptions

Find the Best Local LLM for Your GPU

FitMyLLM helps you find and run AI models on your own hardware. Enter your GPU — whether it's an NVIDIA RTX 4090, RTX 3090, RTX 3060, AMD RX 7900 XTX, or Apple M4 — and get instant recommendations for the best models that fit your VRAM, with speed estimates and ready-to-run Ollama commands.

Our database covers 498 open-source LLMs including Llama 4, Qwen 3.5, DeepSeek R1, DeepSeek V3, Gemma 3, Phi-4, Mistral, and more. Each model includes benchmarks (MMLU-PRO, HumanEval, MATH, IFEval), VRAM requirements at every quantization level (Q4_K_M, Q5_K_M, Q6_K, Q8_0, FP16), and compatibility data for 1,720 GPUs.

Whether you need an AI for coding (Qwen 2.5 Coder, DeepSeek Coder), creative writing, chat, reasoning (DeepSeek R1), or document analysis with RAG — FitMyLLM finds the optimal model for your specific hardware in seconds.

How Much VRAM Do You Need for Local AI?

Running LLMs locally requires GPU VRAM (video memory). The amount depends on model size and quantization: a 7B parameter model at Q4 quantization needs about 4GB VRAM, while a 70B model needs 40GB+. Modern GPUs like the RTX 4060 (8GB), RTX 4070 Ti (12GB), RTX 4080 (16GB), and RTX 4090 (24GB) can run increasingly powerful models.

Speed depends on memory bandwidth, not just compute power. That's why the RTX 3090 (936 GB/s) still competes with the RTX 4090 (1,008 GB/s) for LLM inference. The new RTX 5090 with 1,792 GB/s GDDR7 bandwidth is the fastest consumer GPU for local AI.

Apple Silicon users benefit from unified memory — an M4 Max with 128GB can run 70B models that would require a $2,000+ GPU on PC. FitMyLLM supports all platforms: NVIDIA, AMD, Intel Arc, and Apple M1/M2/M3/M4 chips.

Compare LLM Models

Side-by-side comparison of any models. Benchmark scores, VRAM usage, speed estimates, and radar charts. Compare Llama 4 vs Qwen 3.5, DeepSeek R1 vs Gemma 3, or any combination.

GPU Tier List for AI

Every GPU ranked S-tier to F-tier for running local AI. Based on VRAM, bandwidth, and real model compatibility data — not opinions. Includes NVIDIA RTX, AMD Radeon, Intel Arc, and Apple Silicon.

Enterprise LLM Deployment

Plan production LLM deployments with GPU sizing, P95 latency estimation, and cloud vs on-prem TCO analysis. Supports vLLM, TRT-LLM, and SGLang serving engines.