Raptor V0.5 8B A1B JANG 6M — Hardware Requirements & GPU Compatibility
ChatReasoningFunctions
Raptor V0.5 8B A1B JANG 6M is a 6.2B-parameter open language model from OsaurusAI. It supports a context window of up to 131,072 tokens. At BF16 it needs about 12.92 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 16 GB (BF16 · 64K)Best on 24 GB (BF16 · ~221 tok/s · 128K)Macs from 18 GB (BF16 · ~40 tok/s)
MIT
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Raptor V0.5 8B A1B JANG 6M
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve OsaurusAI/Raptor-v0.5-8B-A1B-JANG_6M --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Other ways
each opens step-by-stepRun in cloud
Fits on RTX 5060 Ti 16GB (2 GB headroom) · BF16
- Generation speed
- ~117 tok/s
- generation speed
- Cost per 1M output tokens
- $0.39
- per 1M output tokens
How Much VRAM Does Raptor V0.5 8B A1B JANG 6M Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 12.9 GB | 13.5 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 128K context · ~221 tok/s |
Selected BF16
Brain floating point 1613.1GBat 16K context
- Weights
- 12.3 GB
- KV cache
- 0.5 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 10.9 GB free · ~221 tok/s
≥50 tok/s needs ≥173 GB/s · RTX 5090 ~320, RTX 3090 Ti ~221
Which Hardware Can Run Raptor V0.5 8B A1B JANG 6M?
BF16 · 12.9 GBRaptor V0.5 8B A1B JANG 6M (BF16) requires 12.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 17+ GB is recommended. Using the full 131K context window can add up to 3.3 GB, bringing total usage to 16.2 GB. 26 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080. 125 devices with unified memory can run Raptor V0.5 8B A1B JANG 6M, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Pro 14" M3 Pro (18 GB).
16–18 GB
16–18 GB tier →fits · 2.9 GB free · up to 64K ctx
18 GPUs · 1 Mac class · 1 device family
RTX 5080~214Simulate output on RTX 5080RTX 5070 Ti~203Simulate output on RTX 5070 TiRTX 4080 SUPER~175Simulate output on RTX 4080 SUPERM3 Pro*18 GB~40Simulate output on MacBook Pro 14" M3 Pro (18 GB)Orin NX~30Simulate output on NVIDIA Jetson Orin NX 16GB20 GB
fits · 6.9 GB free · up to 128K ctx
1 GPU
RX 7900 XT~109Simulate output on RX 7900 XT32–40 GB
fits · 18.9 GB free · up to 128K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~320Simulate output on RTX 5090M5 Max36 GB~88Simulate output on Mac Studio M5 Max (36 GB)M532 GB~41Simulate output on MacBook Air 13" M5 (32 GB)Orin~59Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~38Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
3| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Yi 6B Chat01.AI | — | 4.2 GB | ~161 | same size |
| Chatglm3 6BZ.ai | — | 5.2 GB | ~159 | same size |
| Yi 1.5 6B Chat01.AI | — | 4.2 GB | ~161 | same size |
Specifications
- Publisher
- OsaurusAI
- Parameters
- 6.2B
- Active parameters
- 1B per token
- Architecture
- BailingMoeV3ForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 157,184
- Release Date
- 2026-08-25
- License
- MIT
Frequently Asked Questions
How much VRAM does Raptor V0.5 8B A1B JANG 6M need?
Raptor V0.5 8B A1B JANG 6M requires 12.9 GB of VRAM at BF16. Full 131K context adds up to 3.3 GB (16.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 6.2B × 16 bits ÷ 8 = 12.3 GB
KV Cache + Overhead ≈ 0.6 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 ≈ 3.9 GB (at full 131K context)
VRAM usage by quantization
Can I run Raptor V0.5 8B A1B JANG 6M on a Mac?
Yes — MacBook Pro 14" M3 Pro (18 GB) and 108 other Macs can run Raptor V0.5 8B A1B JANG 6M. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 12.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run Raptor V0.5 8B A1B JANG 6M locally?
Yes — Raptor V0.5 8B A1B JANG 6M can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Raptor V0.5 8B A1B JANG 6M?
At BF16, Raptor V0.5 8B A1B JANG 6M can reach ~191 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~221 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 2.1 GB active ÷ (8000 × 0.65) = 0.404 ms, plus 24 layers × 0.055 ms = 1.320 ms, so 1000 ÷ 1.724 ms = ~580 tok/s
Estimated speed at BF16 (12.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Raptor V0.5 8B A1B JANG 6M?
At BF16, the download is about 12.31 GB.
Which GPUs can run Raptor V0.5 8B A1B JANG 6M?
26 consumer GPUs can run Raptor V0.5 8B A1B JANG 6M at BF16. Top options include AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, AMD Radeon RX 6800. 8 GPUs have plenty of headroom for comfortable inference.
Which devices can run Raptor V0.5 8B A1B JANG 6M?
125 devices with unified memory can run Raptor V0.5 8B A1B JANG 6M at BF16 (12.9 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.