Which GPU for Which LLM — VRAM Requirements by Model (2026)

How to read the VRAM floor

Every floor in this guide comes from the same arithmetic rather than from a vendor chart: Q4_K_M weights run roughly 0.55 GB per billion parameters, and the runtime plus a usable context window wants about 2 GB on top. A 14B model is therefore ~9.7 GB resident, a 32B ~19.6 GB, and a 70B ~40 GB before context. Round up to the nearest card capacity and that is the floor.

The figure that stops being predictable is what happens below the floor. Once weights spill past VRAM the number is set by PCIe and system-memory bandwidth, not by the GPU, and the drop is steep rather than gradual — which is why a tier is quoted as a floor and not as a suggestion. Per-card medians over published runs, with the run counts and sources behind them, live on the benchmark pages; the GPU picker ranks cards that clear a floor by price.

Qwen3 — VRAM floors and GPU picks

Variants 1.7B · 4B · 7B · 14B · 32B · 72B · quantisation Q4_K_M · context 128K · full Qwen3 build guide →

Perfect for chatbot + coding use cases on smaller variants. 16GB lets you run 14B at Q4 with comfortable context.

Llama 4 — VRAM floors and GPU picks

Variants 8B · 17B · 70B · 405B · quantisation Q4_K_M · context 256K · full Llama 4 build guide →

8B Q4 fits in 8 GB but you want 12-16 GB for context room. 8B is a good lightweight assistant; coding and complex reasoning are limited.

DeepSeek V3.2 — VRAM floors and GPU picks

Variants 16B (active 2.4B) · 236B MoE (active 21B) · quantisation Q4_K_M · context 128K · full DeepSeek V3.2 build guide →

16 GB cards run the 16B-dense variant at Q4 cleanly. Avoid 8 GB cards — context window collapses.

Gemma 4 — VRAM floors and GPU picks

Variants 2B · 7B · 9B · 27B · quantisation Q4_K_M · context 128K · full Gemma 4 build guide →

Gemma 4 2B at Q4 fits even on integrated graphics. 7B Q4 needs 8 GB; 12 GB lets you keep full 128K context active.

Phi-4 — VRAM floors and GPU picks

Variants mini (4B) · 14B · quantisation Q4_K_M · context 16K · full Phi-4 build guide →

Phi-4 mini fits on almost any modern card. Quality is solid for a 4B model — beats Llama 3.2 3B on most benchmarks.

Frequently asked questions

Where to go next

• Rank GPUs by VRAM floor, budget and workload — the same mapping, indexed by what you can spend.
• The local-LLM model-fit table — every card SpecPicks holds runs for, bucketed by what it loads at Q4.
• Best GPUs for local LLMs — the ranked buying guide, per VRAM bracket.
• Benchmark data by card — medians, run counts and source links per SKU.