How much VRAM does Gemma 4 31B IT need?

About 21.1 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 23.5 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.

Will Gemma 4 31B IT run on a 24GB GPU?

Yes — at Q4_K_M and 4K context it needs about 21.1 GB, which leaves 2.9 GB spare on a RTX 3090, or on any of the other 24 GB cards here (4 in all). That is the smallest size in this index that clears it comfortably; 26 of 59 do.

Which quantization of Gemma 4 31B IT should I use?

No published quality comparison exists for this model, so pick by footprint: Q4_K_M is the level most people run, and a higher bits-per-weight level is more faithful. All 2 levels in the index are Q4_K_M, Q8_0.

Gemma 4 31B IT

31B

Google Gemma 4

Google's dense Gemma 4 flagship: about 31B parameters, a 256K window and image input. Only 10 of its 60 layers cache the full context, and those use four wide KV heads, so 128K of context adds about 11 GB of cache where a conventional 60-layer design would need about 120 GB. At Q4 it is about 21 GB at 4K — on a 24 GB card that is right at the edge of comfortable, and tight from 32K. A 32 GB card holds 32K comfortably. Sizes use the calculator's generic rates — no GGUF file size could be checked, and no per-level quality loss has been published.

⬇ 9.8M HF downloads♥ 3986 likesgoogle/gemma-4-31B-it· stats from 10/1/2026

Consumer GPUPro GPUMac / Apple Silicon

262K

Max Context

Quant Variants

GGUF Q8_0

Best Quality

—

Accuracy Retained

Calculate VRAM Hugging Face Compare

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Measured = run on this site · Estimated = not run here: calculated, or a figure this site has not verified · Community = public reports

Format	Level	BPW	VRAM	PPL Loss	Speed	Source	Actions
GGUF	Q4_K_M	4.85	18.6 GB	—	—	Estimated	Calc HF
GGUF	Q8_0	8.5	32.6 GB	—	—	Estimated	Calc HF

Similar models

Compare with Gemma 4

26B-A4B

Gemma 4 26B-A4B IT

Google Gemma 4

Consumer GPUPro GPU

15.3 GBmin VRAM—accuracy

Google's Gemma 4 mixture-of-experts model: about 25B parameters in the text model, roughly 4B active per token, a 256K window and image input. Only 5 of its 30 layers keep a cache that grows with context, and those use fewer, wider heads, so the cache stays small — about 0.9 GB at 32K and 5.3 GB at the full 256K. At Q4 that is about 17 GB at 32K: comfortable on a 24 GB card, which can still load the whole window (tight). A 16 GB card is just too small. Sizes use the calculator's generic rates — no GGUF file size could be checked, and no per-level quality loss has been published.

30B-A3B

Qwen3-VL 30B-A3B Instruct

Alibaba Qwen3-VL

Consumer GPUPro GPU

15.2 GBmin VRAM99.7%accuracy

Multimodal MoE with only ~3B active parameters, so it stays responsive on Apple unified memory and survives CPU offload far better than a dense 30B. Q4 ~19GB — a 24GB card holds it outright.

36B

Seed-OSS 36B Instruct

ByteDance Seed

Consumer GPUPro GPU

17.4 GBmin VRAM98.7%accuracy

Dense 36B with a native 512K context. Q4 weights are ~22GB, which lands on a 24GB card or a 2×16GB split — but the context is the real cost: 512K of KV cache is roughly 128GB on its own, so budget context first and weights second.

27B

Qwen3.8 27B

Alibaba Qwen3.8

Consumer GPUPro GPU

15.3 GBmin VRAM—accuracy

Hybrid attention: only 16 of its 64 layers keep a KV cache, which is why a 27B model holds a 262K context in about 16GB of cache rather than 64GB. Sizing it as a conventional stack overstates the cache fourfold — the estimates here count the 16 and match published measurements at 8K, 32K and 262K. Quality loss per level has not been published.

Running Gemma 4 31B IT locally

At Q4_K_M and 4K of context, Gemma 4 31B IT needs about 21.1 GB — 17.7 GB of weights, 1.48 GB of KV cache and a 1.9 GB activation buffer. The smallest cards in this index that clear that comfortably are 24 GB ones — 4 of them, from the RTX 3090 up — and 26 of the 59 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.

What longer context costs

Going from 4K to 32K adds about 2.19 GB, taking the total to 23.5 GB. That is gentler than the parameter count suggests: only 10 of 60 layers keep a KV cache that grows with context, and 50 more cap theirs at a sliding window, so the cache scales at a fraction of the usual rate. The model's native window is 256K; holding all of it at Q4_K_M would need about 43 GB.

Which build to download

This index only tracks Gemma 4 31B IT in GGUF, across 2 levels (Q4_K_M, Q8_0). No per-level perplexity sweep has been published for this model, so the quality column is empty rather than estimated — within one model, more bits per weight is the only ordering the data supports. No throughput has been measured for this model on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 and CUDA only.

Common questions

How much VRAM does Gemma 4 31B IT need?: About 21.1 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 23.5 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.
Will Gemma 4 31B IT run on a 24GB GPU?: Yes — at Q4_K_M and 4K context it needs about 21.1 GB, which leaves 2.9 GB spare on a RTX 3090, or on any of the other 24 GB cards here (4 in all). That is the smallest size in this index that clears it comfortably; 26 of 59 do.
Which quantization of Gemma 4 31B IT should I use?: No published quality comparison exists for this model, so pick by footprint: Q4_K_M is the level most people run, and a higher bits-per-weight level is more faithful. All 2 levels in the index are Q4_K_M, Q8_0.

Where this model fits

Sized at Q4_K_M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory.

Runs comfortably on: RTX 309024GB · +2.9 Radeon RX 7900 XTX24GB · +2.9 RTX 409024GB · +2.9 Tesla P40 24G24GB · +2.9 Mac M5 32G32GB · +2.9
Just misses: Radeon RX 7900 XT+1.1GB over Mac M4 Pro 24G+3.1GB over
Ships in: GGUF
A top pick for: Best local LLM for 24GB Best local LLM for 32GB Best local LLM for Apple silicon
Try it yourself: Size it in the calculator Generate the run command

How to actually run this

Deployment guides for this model and this class of hardware.

This page's figures change when the model or the runtime does.Last updated 2026-10-01 RSS → /feed.xml