CanMyPCRunAILocal AI compatibility

What AI models can you run with 24GB of VRAM?

With 24GB of VRAM, 193 of 225 catalog builds have good/excellent reference fits at 4K context. 15 more run by offloading part of the model to system RAM, which works but is slower.

193

run well

15

with trade-offs

225

builds evaluated

Check my actual PC

Capacity is still finite at 24 GB

A 24 GB card can offer more choices of quantization and context, but it does not mean any large model will fit. Check the largest builds in the table individually. Two 12 GB cards are not treated as one 24 GB card by this engine.

Quantization compresses weights; it does not remove context-cache or runtime costs. Compare the same model at Q4 and Q8 in the calculator, then validate its output on your task. Training and fine-tuning need a different memory budget.

Change system RAM and contextCompare exact builds8 GB vs 12 GB vs 16 GB

Four builds to compare by task

Editorial examples chosen for their documented tasks, all Q4_K_M at 4,096 tokens. Check the verdict before downloading. These are estimates, not benchmark rankings.

Short conversations and summaries

llama3.2:3b

A small instruction-tuned model for trying local chat with more memory headroom. Review summaries against the source text.

Task and build source · Catalog checked 2026-10-13

Excellent fit

Est. memory 2.9 GB · high confidence

Model fully fits in usable GPU VRAM.

ollama run llama3.2:3b

General instruction following

llama3.1:8b

An 8B instruction-tuned alternative to compare on your own prompts. It needs more memory than the 3B example and can still give incorrect answers.

Task and build source · Catalog checked 2026-10-13

Excellent fit

Est. memory 5.8 GB · high confidence

Model fully fits in usable GPU VRAM.

ollama run llama3.1:8b

Code explanation and editing

qwen2.5-coder:7b

A code-focused instruct build. Review generated changes and run your tests; a memory fit is not evidence that its code is correct.

Task and build source · Catalog checked 2026-10-13

Excellent fit

Est. memory 5.3 GB · high confidence

Model fully fits in usable GPU VRAM.

ollama run qwen2.5-coder:7b

A larger general-purpose comparison

qwen2.5:14b

A 14B instruct build for comparing answers when memory allows. Larger size does not establish better results for every task.

Task and build source · Catalog checked 2026-10-13

Excellent fit

Est. memory 10.2 GB · high confidence

Model fully fits in usable GPU VRAM.

ollama run qwen2.5:14b

After opening Ollama's prompt, enter /set parameter num_ctx 4096 to match this calculation, within the model's supported maximum. Install a current Ollama release that supports the build. Setup and troubleshooting.

Models that fit — largest memory first — for 24GB of VRAM

Heaviest first — each of these has a good/excellent reference fit with 24GB at 4K context, counting weights, KV cache, compute buffers and runtime overhead.

Models that fit in 24GB of VRAM
ModelBuildMemory neededVerdict
codeboogacodebooga:34b-v0.1-q4_K_MQ4_K_M~21.5 GBGood fit
phind-codellamaphind-codellama:34b-python-q4_K_MQ4_K_M~21.5 GBGood fit
qwqqwq:32b-preview-q4_K_MQ4_K_M~21.4 GBGood fit
olmo-3.1olmo-3.1:32bQ4_K_M~21.0 GBGood fit
command-rcommand-r:35b-08-2024-q4_K_MQ4_K_M~20.9 GBGood fit
qwen3-coderqwen3-coder:30bQ4_K_M~19.4 GBGood fit
clefclef:27bQ4_K_M~18.5 GBGood fit
qwen3.8qwen3.8:27bQ4_K_M~18.3 GBGood fit
muse-glimmermuse-glimmer:30bQ4_K_M~17.4 GBExcellent fit
mistral-small3.1mistral-small3.1:24bQ4_K_M~16.6 GBExcellent fit
devstral-small-2devstral-small-2:24bQ4_K_M~16.3 GBExcellent fit
mistral-small3.2mistral-small3.2:24bQ4_K_M~16.3 GBExcellent fit
lfm2lfm2:24bQ4_K_M~16.1 GBExcellent fit
devstraldevstral:24bQ4_K_M~15.4 GBExcellent fit
magistralmagistral:24bQ4_K_M~15.4 GBExcellent fit
solar-prosolar-pro:22bQ4_K_M~15.0 GBExcellent fit
mistral-smallmistral-small:22b-instruct-2409-q4_K_MQ4_K_M~14.7 GBExcellent fit
codestralcodestral:22b-v0.1-q4_K_MQ4_K_M~14.7 GBExcellent fit
gpt-ossgpt-oss:20bMXFP4~14.5 GBExcellent fit
gpt-oss-safeguardgpt-oss-safeguard:20bMXFP4~14.5 GBExcellent fit
phi4-reasoningphi4-reasoning:14bQ4_K_M~12.4 GBExcellent fit
deepseek-coder-v2deepseek-coder-v2:16b-lite-base-q4_K_MQ4_K_M~11.9 GBExcellent fit
deepseek-v2deepseek-v2:16b-lite-chat-q4_K_MQ4_K_M~11.9 GBExcellent fit
everythinglmeverythinglm:13b-16k-q4_K_MQ4_K_M~11.4 GBExcellent fit
nexusravennexusraven:13b-q4_K_MQ4_K_M~11.4 GBExcellent fit

Graphics cards with 24GB of VRAM

GeForce RTX 4090GeForce RTX 3090Radeon RX 7900 XTX

How this was calculated

Every model is evaluated at 4K context against 24GB of VRAM, minus a reserve for the display and operating system, and assuming 32GB of system RAM with an illustrative 8-core/16-thread CPU and 500GB free disk. Available RAM and GPU budget/free memory are unknown. A working Vulkan backend on Windows is assumed; this is a capacity scenario, not a claim that all cards with this much memory have the same support. Your own machine may differ, which is what the PC scan measures directly.

24GB VRAM and local AI — frequently asked questions

Is 24GB of VRAM enough to run AI models locally?
Yes — 193 of the 225 builds evaluated have good/excellent reference fits with 24GB at 4K context, and 15 more run with part of the model offloaded to system RAM. The heaviest that fits is codebooga:34b-v0.1-q4_K_M, needing about 21.5 GB.
How should I choose a model for 24GB VRAM?
Choose for your task, then check memory. codebooga (codebooga:34b-v0.1-q4_K_M) is the heaviest catalog default that fits this reference budget; its size does not establish answer quality. Smaller models leave headroom for a longer context window, which often matters more than raw parameter count.
Which graphics cards have 24GB of VRAM?
Cards with 24GB include GeForce RTX 4090, GeForce RTX 3090, Radeon RX 7900 XTX.

Other VRAM amounts

4GB6GB8GB10GB12GB16GB32GB