orcarouter·Orca·Qwen3_5ForCausalLM

OrcaSAQ 2 27B — Hardware Requirements & GPU Compatibility

ChatReasoningFunctions

OrcaSAQ 2 27B is a 6.8B-parameter open language model from orcarouter in the Orca family. It supports a context window of up to 262,144 tokens. At BF16 it needs about 14.29 GB of VRAM — see which GPUs and Macs can run it below.

3.7K downloads 254 likes262K context
Based on Qwen3.8 27B

Specifications

Publisher
orcarouter
Family
Orca
Parameters
6.8B
Architecture
Qwen3_5ForCausalLM
Context Length
262,144 tokens
Vocabulary Size
248,320
Release Date
2026-09-24
License
Apache 2.0

Get Started

How Much VRAM Does OrcaSAQ 2 27B Need?

Select a quantization to see compatible GPUs below.

QuantizationBitsVRAM
BF16est.16.0014.3 GB

est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.

Which GPUs Can Run OrcaSAQ 2 27B?

BF16 · 14.3 GB

OrcaSAQ 2 27B (BF16) requires 14.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 19+ GB is recommended. Using the full 262K context window can add up to 56.8 GB, bringing total usage to 71.1 GB. 26 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080.

Which Devices Can Run OrcaSAQ 2 27B?

BF16 · 14.3 GB

47 devices with unified memory can run OrcaSAQ 2 27B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 (16 GB).

Runs great

— Plenty of headroom
NVIDIA DGX H100~1219 tok/sNVIDIA DGX A100 640GB~742 tok/sMac Studio (M3 Ultra, 256GB)~40 tok/sMac Studio (M3 Ultra, 512GB)~40 tok/sMac Studio (M3 Ultra, 96GB)~40 tok/sMac Pro M2 Ultra (192 GB)~39 tok/sMac Studio M2 Ultra (192 GB)~39 tok/sMacBook Pro 16" M5 Max (128 GB)~30 tok/sMac Studio M4 Max (128 GB)~27 tok/sMac Studio M4 Max (64 GB)~27 tok/sMacBook Pro 16" M4 Max (48 GB)~27 tok/sMacBook Pro 16" M4 Max (64 GB)~27 tok/sMac Studio M4 Max (36 GB)~20 tok/sMacBook Pro 14" M4 Max (36 GB)~20 tok/sMacBook Pro 16" M3 Max (48 GB)~20 tok/sMacBook Pro 14-inch (M5 Pro)~15 tok/sMac Mini M4 Pro (24 GB)~13 tok/sMac Mini M4 Pro (48 GB)~13 tok/sMacBook Pro 14" M4 Pro (24 GB)~13 tok/sMacBook Pro 16" M4 Pro (24 GB)~13 tok/sASUS Ascent GX10~12 tok/sNVIDIA DGX Spark~12 tok/sNVIDIA Jetson AGX Thor Developer Kit~12 tok/sAsus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB)~12 tok/sBeelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB)~12 tok/sFramework Desktop (Ryzen AI Max+ 395, 128 GB)~12 tok/sGMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB)~12 tok/sHP Z2 Mini G1a (Ryzen AI Max+ PRO 395, 128 GB)~12 tok/sHP ZBook Ultra G1a 14 (Ryzen AI Max+ PRO 395, 128 GB)~12 tok/sMinisforum MS-S1 MAX (Ryzen AI Max+ 395, 128 GB)~12 tok/sSnapdragon X2 Elite Extreme Copilot+ PC~10 tok/sNVIDIA Jetson AGX Orin 32GB~9 tok/sNVIDIA Jetson AGX Orin 64GB~9 tok/sMacBook Pro 14-inch (M5)~8 tok/sSnapdragon X Elite Copilot+ PC~6 tok/sMac Mini M4 (32 GB)~6 tok/sMacBook Air 13" M4 (24 GB)~6 tok/sMacBook Air 15" M4 (24 GB)~6 tok/sAMD Ryzen AI 9 HX 370 (Strix Point) Laptop~5 tok/sMacBook Air 13" M3 (24 GB)~5 tok/sIntel Core Ultra 9 288V (Lunar Lake) Laptop~5 tok/s

Related Models

Frequently Asked Questions

How much VRAM does OrcaSAQ 2 27B need?

OrcaSAQ 2 27B requires 14.3 GB of VRAM at BF16. Full 262K context adds up to 56.8 GB (71.1 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 6.8B × 16 bits ÷ 8 = 13.5 GB

KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)

KV Cache + Overhead ≈ 57.6 GB (at full 262K context)

VRAM usage by quantization

14.3 GB
71.1 GB

Learn more about VRAM estimation →

Can I run OrcaSAQ 2 27B on a Mac?

OrcaSAQ 2 27B requires at least 14.3 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.

Can I run OrcaSAQ 2 27B locally?

Yes — OrcaSAQ 2 27B can run locally on consumer hardware. At BF16 quantization it needs 14.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is OrcaSAQ 2 27B?

At BF16, OrcaSAQ 2 27B can reach ~336 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~46 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 ÷ 14.3 × 0.65 = ~364 tok/s

Estimated speed at BF16 (14.3 GB)

~364 tok/s
~46 tok/s
~364 tok/s
~336 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 OrcaSAQ 2 27B?

At BF16, the download is about 13.54 GB.

Which GPUs can run OrcaSAQ 2 27B?

26 consumer GPUs can run OrcaSAQ 2 27B at BF16 (14.3 GB). 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 OrcaSAQ 2 27B?

49 devices with unified memory can run OrcaSAQ 2 27B at BF16 (14.3 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (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.