RemekGemma4ForConditionalGeneration

Basal Omni 1.0 Ultra — Hardware Requirements & GPU Compatibility

ChatVisionFunctions

Basal Omni 1.0 Ultra is a 31.3B-parameter open language model from Remek. 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 2.0Oct 20261.1K downloads28 likes

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.

Decent on a 24 GB GPU

Runs on 24 GB (Q4_K_M · ~32 tok/s · 32K)Macs from 24 GB (Q4_K_M · ~11 tok/s)

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Basal Omni 1.0 Ultra

One recommended way. Every other method, OS and quant is in the step-by-step guide.

Other ways

each opens step-by-step

Run in cloud

Fits on RTX PRO 4500 (32 GB) (10 GB headroom) · Q4_K_M

Generation speed: ~29 tok/s; generation speed
Cost per 1M output tokens: $3.30; per 1M output tokens

Deployon RunPodBest optionfrom $0.34/hr

Compare GPUs →

Run Basal Omni 1.0 Ultra

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

Ollama is not available

No GGUF repository is listed for this model.

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 Remek/basal-omni-1.0-ultra --max-model-len 16384
Runs the original weights, not the Q4_K_M GGUF; needs ~69 GB of GPU memory.

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 PRO 4500 (32 GB)CheapestCheapest10 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 A6000 (48 GB)26 GB free	~25 tok/s	$4.58	Deploy on Vast.aifrom $0.40/hr (opens in new tab)	48 GB · 26 GB free · ~25 tok/s · $4.58 / 1M tokens
RTX 5000 Ada (32 GB)10 GB free	~18 tok/s	$6.50	Deploy on Vast.aifrom $0.43/hr (opens in new tab)	32 GB · 10 GB free · ~18 tok/s · $6.50 / 1M tokens
A40 (48 GB)26 GB free	~22 tok/s	$6.70	Deploy on Vast.aifrom $0.54/hr (opens in new tab)	48 GB · 26 GB free · ~22 tok/s · $6.70 / 1M tokens
A100 40GB18 GB free	~50 tok/s	$3.64	Deploy on Vast.aifrom $0.65/hr (opens in new tab)	18 GB free · ~50 tok/s · $3.64 / 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 →

How Much VRAM Does Basal Omni 1.0 Ultra Need?

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

VRAM	+32K	+128K	File	Quality	On RTX 4090 (reference)
14.9 GB	18.4 GB	31 GB	~13.3 GB	2-bit · K-quant — 2-bit quantization with K-quant improvements	Fits: 64K context · ~44 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
20.4 GB	23.8 GB	36.5 GB	~18.8 GB	4-bit medium — 4-bit medium quantization — most popular sweet spot	Fits: 32K context · ~32 tok/s
23.9 GB	27.3 GB	40 GB	~22.3 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	~25.8 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	~31.3 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	~62.6 GB	16-bit · bfloat — Brain floating point 16 — preferred for training	Does not fit: needs 65.5 GB

est.calculated, no published file yet

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 Basal Omni 1.0 Ultra?

Q4_K_M · 20.4 GB

Basal Omni 1.0 Ultra (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 Basal Omni 1.0 Ultra, 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

8–16 GB · RTX 4060, RTX 3060 12GB, RTX 5060 Ti 16GBDoesn't fit — smallest quant needs 16.2 GB8 GB tier →12 GB tier →16 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 Basal Omni 1.0 Ultra

Similar models

6tok/s on RTX 4090

Model	Score	VRAM	tok/s	Why it is similar
Hy Memory 30B A3BTencent	—	19.1 GB	~184	same size
Granite Switch 4.1 30BIBM	—	22.7 GB	~35	same size
Muse Glimmer 30BMeta	—	19.6 GB	~36	same size
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA	—	19.3 GB	~197	same size
Hy MT2 30B A3BTencent	—	19.1 GB	~170	same size
Gemma 4 31BGoogle	—	21.7 GB	~32	same size

Specifications

Publisher: Remek
Parameters: 31.3B
Architecture: Gemma4ForConditionalGeneration
Context Length: 262,144 tokens
Vocabulary Size: 262,144
Release Date: 2026-10-15
License: Apache 2.0

Resources

Hugging Face model card (opens in a new tab)

Frequently Asked Questions

How much VRAM does Basal Omni 1.0 Ultra need?

Basal Omni 1.0 Ultra 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 Basal Omni 1.0 Ultra?

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 Basal Omni 1.0 Ultra?

For Basal Omni 1.0 Ultra, Q4_K_M (20.4 GB) offers the best balance of quality and VRAM usage. Q5_K_M (23.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 14.9 GB.

VRAM requirement by quantization

Q2_K

14.9 GB~75%

Q4_K_M ★

20.4 GB~89%

Q5_K_M

23.9 GB~92%

Q6_K

27.4 GB~95%

Q8_0

32.9 GB~99%

BF16

64.2 GB~100%

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Basal Omni 1.0 Ultra on a Mac?

Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run Basal Omni 1.0 Ultra. 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).

Can I run Basal Omni 1.0 Ultra locally?

Yes — Basal Omni 1.0 Ultra can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Basal Omni 1.0 Ultra?

At Q4_K_M, Basal Omni 1.0 Ultra 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 Basal Omni 1.0 Ultra?

At Q4_K_M, the download is about 18.76 GB. The full-precision BF16 version is 62.55 GB. The smallest option (Q2_K) is 13.29 GB.

Which GPUs can run Basal Omni 1.0 Ultra?

7 consumer GPUs can run Basal Omni 1.0 Ultra 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 Basal Omni 1.0 Ultra?

122 devices with unified memory can run Basal Omni 1.0 Ultra 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.

Basal Omni 1.0 Ultra — Hardware Requirements & GPU Compatibility

Decent on a 24 GB GPU

Run Basal Omni 1.0 Ultra

Recommended

Other ways

Run in cloud

Run Basal Omni 1.0 Ultra

Install vLLM

Serve the model

All sources

How Much VRAM Does Basal Omni 1.0 Ultra Need?

Selected Q4_K_M

Which Hardware Can Run Basal Omni 1.0 Ultra?

Alternatives to Basal Omni 1.0 Ultra

Similar models

Specifications

Resources

Frequently Asked Questions

Run Basal Omni 1.0 Ultra

Install vLLM

Serve the model

All sources