llmrun
XCurOSXCurOSForCausalLM

XCurOS0.1 8B Instruct — Hardware Requirements & GPU Compatibility

ChatFunctions

XCurOS0.1 8B Instruct is a 7.6B-parameter open language model from XCurOS. It supports a context window of up to 32,768 tokens. At BF16 it needs about 15.65 GB of VRAM — see which GPUs and Macs can run it below.

7.6B params · dense33K contextOther51.7K downloads4 likes
A

Runs well on a 24 GB GPU

Runs from16 GB BF16 · 8KBest on24 GB BF16 · ~42 tok/s · 32KMacs from24 GB BF16 · ~14 tok/s

Other

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run XCurOS0.1 8B Instruct

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

vLLM
one command · needs vLLM installed
$vllm serve XCurOS/XCurOS0.1-8B-Instruct --max-model-len 16384

vLLM repo with its own quantisation

Download: Weights on Hugging Face

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on RTX 3090 (24 GB) (7 GB headroom) · BF16

Generation speed
~39 tok/s
generation speed
Cost per 1M output tokens
$1.41
per 1M output tokens
Deployon Vast.aiBest valuefrom $0.20/hr (opens in new tab)
Compare GPUs →
or

How Much VRAM Does XCurOS0.1 8B Instruct Need?

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

QuantizationVRAM+32KOn RTX 4090 (reference)
15.7 GB17.4 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingFits: 32K context · ~42 tok/s
est.calculated, no published file yet

Selected BF16

Brain floating point 16

16.5GBat 16K context

Weights
15.2 GB
KV cache
0.9 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 7.5 GB free · ~42 tok/s

≥50 tok/s needs ≥1.20 TB/s · RTX 5090 ~74

Which Hardware Can Run XCurOS0.1 8B Instruct?

BF16 · 15.7 GB

XCurOS0.1 8B Instruct (BF16) requires 15.7 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 21+ GB is recommended. Using the full 33K context window can add up to 1.8 GB, bringing total usage to 17.4 GB. 26 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080. 122 devices with unified memory can run XCurOS0.1 8B Instruct, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).

By VRAM tier · typical GPUs and Macs at BF16
8–12 GB · RTX 4060, RTX 3060 12GBDoesn't fit — smallest quant needs 16.5 GB8 GB tier →12 GB tier →
16 GB · RTX 5060 Ti 16GBBF16 · 16.5 GB · ~19 tok/s · 8Ktight16 GB tier →
24 GB · RTX 4090referenceBF16 · 16.5 GB · ~42 tok/s · 32K24 GB tier →
Mac 32 GB · Mac Mini M4BF16 · 16.5 GB · ~5 tok/s · 32KMacs →
Mac 64 GB · Mac Studio M4 MaxBF16 · 16.5 GB · ~24 tok/s · 32KMacs →

Alternatives to XCurOS0.1 8B Instruct

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
Ling 3.0 TinyInclusion AI—5.5 GB~364same size
BitCPM CANN 8BOpenBMB—5.6 GB~127same size
Gemma 4 E4BGoogle—5.6 GB~123same size
Olmo 3 7B InstructAllen AI—8.4 GB~114same size
Phi Mini MoE InstructMicrosoft—5.4 GB~239same size
Gemma 3n E4B ITGoogle—7.7 GB~127same size

Specifications

Publisher
XCurOS
Parameters
7.6B
Architecture
XCurOSForCausalLM
Context Length
32,768 tokens
Vocabulary Size
152,064
Release Date
2026-02-28
License
Other

Resources

Frequently Asked Questions

How much VRAM does XCurOS0.1 8B Instruct need?

XCurOS0.1 8B Instruct requires 15.7 GB of VRAM at BF16. Full 33K context adds up to 1.8 GB (17.4 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 7.6B × 16 bits ÷ 8 = 15.2 GB

KV Cache + Overhead ≈ 0.5 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 ≈ 2.2 GB (at full 33K context)

VRAM usage by quantization

15.7 GB
17.4 GB

Learn more about VRAM estimation →

Can I run XCurOS0.1 8B Instruct on a Mac?

Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run XCurOS0.1 8B Instruct. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 15.7 GB of usable unified memory (RAM minus macOS overhead).

Can I run XCurOS0.1 8B Instruct locally?

Yes — XCurOS0.1 8B Instruct can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is XCurOS0.1 8B Instruct?

At BF16, XCurOS0.1 8B Instruct can reach ~307 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~42 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 ÷ 15.65 × 0.65 = ~332 tok/s

Estimated speed at BF16 (15.7 GB)

~332 tok/s
~42 tok/s
~332 tok/s
~307 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 XCurOS0.1 8B Instruct?

At BF16, the download is about 15.23 GB.

Which GPUs can run XCurOS0.1 8B Instruct?

26 consumer GPUs can run XCurOS0.1 8B Instruct at BF16. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3090 Ti, AMD Radeon RX 6800. 7 GPUs have plenty of headroom for comfortable inference.

Which devices can run XCurOS0.1 8B Instruct?

122 devices with unified memory can run XCurOS0.1 8B Instruct at BF16 (15.7 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.