kawaimasaGemma 4Gemma4ForConditionalGeneration

Wanabi Gemma4 31B — Hardware Requirements & GPU Compatibility

Chat

Wanabi Gemma4 31B is a 31.3B-parameter open language model from kawaimasa in the Gemma 4 family. It supports a context window of up to 262,144 tokens. At Q4_K_M it needs about 20.39 GB of VRAM — see which GPUs and Macs can run it below.

31.3B params · dense262K contextApache 2.0May 2026239 downloads2 likes5.1K quant downloads

Based on Gemma 4 31B IT

Your hardware

Verdicts below are for the reference RTX 4090. Set yours to personalise the page.

Detection reads your browser's GPU name with no data sent anywhere.

B

Decent on a 24 GB GPU

Runs from 12 GB (IQ2_XXS · 16K)Best on 24 GB (Q4_K_M · ~32 tok/s · 32K)Macs from 16 GB (IQ2_XS · ~13 tok/s)

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Wanabi Gemma4 31B

One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.

Recommended

Ollama

one command · needs Ollama installed

$ollama run hf.co/kawaimasa/Wanabi-Gemma4-31B-GGUF:Q4_K_M

Q4_K_M fits fully on the RTX 4090 · 2.3 GB free · 16K context

Download: Wanabi-Gemma4-31B-Q4_K_M.gguf18.69 GBkawaimasa

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on RTX 5090 (32 GB) (10 GB headroom) · Q4_K_M

Generation speed: ~57 tok/s; generation speed
Cost per 1M output tokens: $2.42; per 1M output tokens

Deployon Vast.aiBest valuefrom $0.50/hr

Compare GPUs →

or

How Much VRAM Does Wanabi Gemma4 31B Need?

Select a quantization level; the listed hardware adheres to it.

Quantization	VRAM	+32K	+128K	File	Quality	On RTX 4090 (reference)
	10.2 GB	13.7 GB	26.3 GB	8.7 GB	2-bit · i-quant extreme compression — Importance-weighted 2-bit, extreme compression — significant quality loss	Fits: 64K context · ~64 tok/s
	11 GB	14.4 GB	27.1 GB	9.5 GB	2-bit · i-quant extra small — Importance-weighted 2-bit, extra small	Fits: 64K context · ~60 tok/s
	12.2 GB	15.6 GB	28.3 GB	10.9 GB	2-bit · i-quant medium — Importance-weighted 2-bit, medium	Fits: 64K context · ~54 tok/s
	14.1 GB	17.6 GB	30.3 GB	11 GB	2-bit · small K-quant — 2-bit small K-quant	Fits: 64K context · ~46 tok/s
	14.5 GB	18 GB	30.6 GB	13.1 GB	3-bit · i-quant extra small — Importance-weighted 3-bit, extra small	Fits: 64K context · ~45 tok/s
	14.9 GB	18.4 GB	31 GB	13.8 GB	3-bit · i-quant small — Importance-weighted 3-bit, small	Fits: 64K context · ~44 tok/s
	14.9 GB	18.4 GB	31 GB	11.9 GB	2-bit · K-quant — 2-bit quantization with K-quant improvements	Fits: 64K context · ~44 tok/s
	15.3 GB	18.7 GB	31.4 GB	13.8 GB	3-bit small — 3-bit small quantization	Fits: 64K context · ~43 tok/s
	15.7 GB	19.1 GB	31.8 GB	14.4 GB	3-bit · i-quant medium — Importance-weighted 3-bit, medium	Fits: 64K context · ~42 tok/s
	16.9 GB	20.3 GB	33 GB	15.3 GB	3-bit medium — 3-bit medium quantization	Fits: 32K context · ~39 tok/s
	17.3 GB	20.7 GB	33.4 GB	17.7 GB	4-bit · legacy — 4-bit legacy quantization	Fits: 32K context · ~38 tok/s
	17.6 GB	21.1 GB	33.8 GB	16.6 GB	3-bit large — 3-bit large quantization	Fits: 32K context · ~37 tok/s
	18.4 GB	21.9 GB	34.6 GB	16.7 GB	4-bit · i-quant compact — Importance-weighted 4-bit, compact	Fits: 32K context · ~36 tok/s
	19.2 GB	22.7 GB	35.3 GB	17.8 GB	4-bit small — 4-bit small quantization	Fits: 32K context · ~34 tok/s
	19.2 GB	22.7 GB	35.3 GB	19.5 GB	4-bit · legacy+ — 4-bit legacy quantization with offset	Fits: 32K context · ~34 tok/s
	19.2 GB	22.7 GB	35.3 GB	17.7 GB	4-bit · i-quant non-linear — Importance-weighted 4-bit, non-linear	Fits: 32K context · ~34 tok/s
	20.4 GB	23.8 GB	36.5 GB	18.7 GB	4-bit medium — 4-bit medium quantization — most popular sweet spot	Fits: 32K context · ~32 tok/s
	21.2 GB	24.6 GB	37.3 GB	21.3 GB	5-bit · legacy — 5-bit legacy quantization	Fits: 16K context · ~31 tok/s
	23.1 GB	26.6 GB	39.2 GB	23.1 GB	5-bit · legacy+ — 5-bit legacy quantization with offset	Fits: 8K context · ~28 tok/s
	23.1 GB	26.6 GB	39.2 GB	21.3 GB	5-bit small — 5-bit small quantization	Fits: 8K context · ~28 tok/s
	23.9 GB	27.3 GB	40 GB	21.8 GB	5-bit medium — 5-bit medium quantization — good quality/size tradeoff	Fits: 4K context · ~27 tok/s
	27.4 GB	30.9 GB	43.5 GB	25.2 GB	6-bit, very good — 6-bit quantization, very good quality	Does not fit: needs 28.7 GB
	32.9 GB	36.3 GB	49 GB	32.6 GB	8-bit, near-lossless — 8-bit quantization, near-lossless	Does not fit: needs 34.2 GB
	64.2 GB	67.6 GB	80.3 GB	61.4 GB	16-bit · bfloat — Brain floating point 16 — preferred for training	Does not fit: needs 65.5 GB

Selected Q4_K_M

4-bit medium quantization

21.7GBat 16K context

Weights: 18.8 GB
KV cache: 2.6 GB
Overhead: 0.3 GB

Fits RTX 4090 (reference) · 2.3 GB free · ~32 tok/s

≥50 tok/s needs ≥1.57 TB/s · RTX 5090 ~57

Which Hardware Can Run Wanabi Gemma4 31B?

Q4_K_M · 20.4 GB

Wanabi Gemma4 31B (Q4_K_M) requires 20.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 27+ GB is recommended. Using the full 262K context window can add up to 33.0 GB, bringing total usage to 53.4 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Wanabi Gemma4 31B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M

Typical hardwareQuantVRAMtok/sContext that fits

8 GB · RTX 4060Doesn't fit — smallest quant needs 11.5 GB8 GB tier →

12 GB · RTX 3060 12GBIQ2_XXS · 11.5 GB · ~23 tok/s · 16K11.5~2316K12 GB tier →

16 GB · RTX 5060 Ti 16GBIQ3_XS · 15.8 GB · ~20 tok/s · 16K15.8~2016K16 GB tier →

24 GB · RTX 4090referenceQ4_K_M · 21.7 GB · ~32 tok/s · 32K21.7~3232K24 GB tier →

Mac 32 GB · Mac Mini M4Q4_K_M · 21.7 GB · ~4 tok/s · 64K21.7~464KMacs →

Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 21.7 GB · ~19 tok/s · 256K21.7~19256KMacs →

Alternatives to Wanabi Gemma4 31B

Gemma 4 family · 35 models →

Similar models

6tok/s on RTX 4090

Model	Score	VRAM	tok/s	Why it is similar
Nanbeige4.3 33BNanbeige	—	23.7 GB	~32	same size
Hy Memory 30B A3BTencent	—	19.1 GB	~184	same size
Granite Switch 4.1 30BIBM	—	22.7 GB	~35	same size
Llm Jp 4.1 32B A3b Thinkingllm-jp	—	20.1 GB	~188	same size
Llm Jp 4.1 33B Thinkingllm-jp	—	22.5 GB	~35	same size
Agnes 3.0 FlashAgnes-AI	—	22.1 GB	~35	same size

Specifications

Publisher: kawaimasa
Family: Gemma 4
Parameters: 31.3B
Architecture: Gemma4ForConditionalGeneration
Context Length: 262,144 tokens
Vocabulary Size: 262,144
Release Date: 2026-05-31
License: Apache 2.0

Resources

Frequently Asked Questions

How much VRAM does Wanabi Gemma4 31B need?

Wanabi Gemma4 31B requires 20.4 GB of VRAM at Q4_K_M, or 64.2 GB at BF16. Full 262K context adds up to 33.0 GB (53.4 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 31.3B × 4.8 bits ÷ 8 = 18.8 GB

KV Cache + Overhead ≈ 1.6 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

KV Cache + Overhead ≈ 34.6 GB (at full 262K context)

VRAM usage by quantization

Q4_K_M

20.4 GB

Q4_K_M + full context

53.4 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 4090 run Wanabi Gemma4 31B?

Yes, at Q5_K_M (23.9 GB) or lower. Higher quantizations like Q6_K (27.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.

What's the best quantization for Wanabi Gemma4 31B?

For Wanabi Gemma4 31B, Q4_K_M (20.4 GB) offers the best balance of quality and VRAM usage. Q5_0 (21.2 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 10.2 GB.

VRAM requirement by quantization

IQ2_XXS

10.2 GB~53%

Q2_K

14.9 GB~75%

IQ4_XS

18.4 GB~87%

Q4_K_M ★

20.4 GB~89%

Q5_0

21.2 GB~90%

BF16

64.2 GB~100%

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Wanabi Gemma4 31B on a Mac?

Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Wanabi Gemma4 31B, the smallest at IQ2_XS. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 20.4 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).

Can I run Wanabi Gemma4 31B locally?

Yes — Wanabi Gemma4 31B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Wanabi Gemma4 31B?

At Q4_K_M, Wanabi Gemma4 31B can reach ~235 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~32 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = (bandwidth GB/s ÷ model GB) × efficiency

Example: NVIDIA B200 → 8000 ÷ 20.4 × 0.65 = ~255 tok/s

Estimated speed at Q4_K_M (20.4 GB)

NVIDIA B200

~255 tok/s

NVIDIA GeForce RTX 4090

~32 tok/s

NVIDIA B300

~255 tok/s

AMD Instinct MI350X

~235 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Wanabi Gemma4 31B?

At Q4_K_M, the download is about 18.76 GB. The full-precision BF16 version is 62.55 GB. The smallest option (IQ2_XXS) is 8.60 GB.

Which GPUs can run Wanabi Gemma4 31B?

7 consumer GPUs can run Wanabi Gemma4 31B at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU has plenty of headroom for comfortable inference.

Which devices can run Wanabi Gemma4 31B?

122 devices with unified memory can run Wanabi Gemma4 31B at Q4_K_M (20.4 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.

Run Wanabi Gemma4 31B

21.7 GB VRAM at 16K context · fits the RTX 4090 (2.3 GB free)

Works on macOS, Windows and Linux.

Install Ollama (Linux)
$curl -fsSL https://ollama.com/install.sh | sh
Install Ollama (macOS / Windows)
Download and run the app; it installs the ollama command.
Download Ollama ↗
Run Q4_K_M
$ollama run hf.co/kawaimasa/Wanabi-Gemma4-31B-GGUF:Q4_K_M
Raise the context window
Type it inside the chat. For the API server instead, start it with OLLAMA_CONTEXT_LENGTH=16384 ollama serve.
$/set parameter num_ctx 16384
A larger context needs more memory than the weights alone.
Use the API
Ollama serves its API on http://localhost:11434.

Works on macOS, Windows and Linux.

Install LM Studio
Desktop app for macOS (Apple silicon), Windows and Linux.
lmstudio.ai ↗
Download the model
In the app press Ctrl/Cmd + Shift + M and paste https://huggingface.co/kawaimasa/Wanabi-Gemma4-31B-GGUF, then pick Q4_K_M. Or use the CLI (run LM Studio once first):
$lms get https://huggingface.co/kawaimasa/Wanabi-Gemma4-31B-GGUF@Q4_K_M
Open on Hugging Face ↗
Load and chat
Open the model loader, select the model and set Context Length to 16384. Leave GPU offload at maximum if it fits.
Start the local server (optional)
$lms server start

Works on macOS, Windows and Linux.

Install llama.cpp (macOS)
MacPorts, Nix and conda-forge also work.
$brew install llama.cpp
Install options ↗
Install llama.cpp (Windows)
$winget install llama.cpp
Install llama.cpp (Linux)
Download the prebuilt llama-*-bin-ubuntu-* archive for your GPU backend (CPU, Vulkan) from the releases page, unpack it and run the binaries from that folder. Homebrew (brew install llama.cpp) and conda-forge also work on Linux.
llama.cpp releases ↗
Start the server
Downloads the model on first run. The chat UI and an OpenAI-compatible API are at http://localhost:8080.
$llama-server -hf kawaimasa/Wanabi-Gemma4-31B-GGUF:Q4_K_M -c 16384 -ngl 99 --port 8080

Works on macOS, Windows and Linux.

Linux only.

Install vLLM
Linux only; on Windows run it inside WSL2. NVIDIA GPU shown; AMD ROCm, Intel and CPU builds have their own install pages.
$uv venv --python 3.12 --seed
$source .venv/bin/activate
$uv pip install vllm --torch-backend=auto
vLLM installation ↗
Serve the model
OpenAI-compatible API at http://localhost:8000/v1.
$vllm serve kawaimasa/Wanabi-Gemma4-31B --max-model-len 16384
Runs the original weights, not the Q4_K_M GGUF; needs ~69 GB of GPU memory.

Works on macOS, Windows and Linux.

Install Jan
jan.ai ↗
Find the model
Open the Hub tab, paste this model ID in Search, and choose Q4_K_M if offered.
$kawaimasa/Wanabi-Gemma4-31B-GGUF
Use the local API (optional)
Settings > Local API Server > Start Server. It listens on http://127.0.0.1:1337.

Rent GPUs hourly to run Q4_K_M right there. Pricing comes from partner marketplaces and varies.

Available GPU rentals for Q4_K_M, prioritized by value
GPU	Speed	$/1M tokens	Rent
RTX 5090 (32 GB)CheapestCheapest10 GB free	~57 tok/s	$2.42	Deploy on Vast.aifrom $0.50/hr (opens in new tab)	32 GB · 10 GB free · ~57 tok/s · $2.42 / 1M tokens
RTX PRO 4500 (32 GB)10 GB free	~29 tok/s	$3.30	Deploy on RunPodfrom $0.34/hr (opens in new tab)	32 GB · 10 GB free · ~29 tok/s · $3.30 / 1M tokens
A40 (48 GB)26 GB free	~22 tok/s	$4.38	Deploy on RunPodfrom $0.35/hr (opens in new tab)	48 GB · 26 GB free · ~22 tok/s · $4.38 / 1M tokens
RTX PRO 4500 (32 GB)10 GB free	~29 tok/s	$3.45	Deploy on Vast.aifrom $0.36/hr (opens in new tab)	32 GB · 10 GB free · ~29 tok/s · $3.45 / 1M tokens
RTX A6000 (48 GB)26 GB free	~25 tok/s	$4.59	Deploy on Vast.aifrom $0.40/hr (opens in new tab)	48 GB · 26 GB free · ~25 tok/s · $4.59 / 1M tokens
A100 40GB18 GB free	~50 tok/s	$3.42	Deploy on Vast.aifrom $0.61/hr (opens in new tab)	18 GB free · ~50 tok/s · $3.42 / 1M tokens
L40 (48 GB)26 GB free	~28 tok/s	$6.97	Deploy on RunPodfrom $0.69/hr (opens in new tab)	48 GB · 26 GB free · ~28 tok/s · $6.97 / 1M tokens
RTX 5090 (32 GB)10 GB free	~57 tok/s	$3.36	Deploy on RunPodfrom $0.69/hr (opens in new tab)	32 GB · 10 GB free · ~57 tok/s · $3.36 / 1M tokens

Compare GPUs →