WhiteRabbitNeo 13B V1 — Hardware Requirements & GPU Compatibility
Chat
WhiteRabbitNeo 13B V1 is a 13B-parameter open language model from WhiteRabbitNeo. It supports a context window of up to 16,384 tokens. At Q4_K_M it needs about 9.78 GB of VRAM — see which GPUs and Macs can run it below.
2.9K downloads
459 likesSpecifications
- Publisher
- WhiteRabbitNeo
- Parameters
- 13B
- Architecture
- LlamaForCausalLM
- Context Length
- 16,384 tokens
- Vocabulary Size
- 32,016
- Release Date
- 2023-12-17
- License
- Llama 2 Community
Get Started
HuggingFace
How Much VRAM Does WhiteRabbitNeo 13B V1 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 7.5 GB | 19.3 GB | 5.53 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 7.7 GB | 19.4 GB | 5.69 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 8.3 GB | 20.1 GB | 6.34 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 9.8 GB | 21.5 GB | 7.80 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 11.2 GB | 23.0 GB | 9.26 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 12.7 GB | 24.4 GB | 10.72 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 15.0 GB | 26.7 GB | 13.00 GB | 8-bit quantization, near-lossless |
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 WhiteRabbitNeo 13B V1?
Q4_K_M · 9.8 GBWhiteRabbitNeo 13B V1 (Q4_K_M) requires 9.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 13+ GB is recommended. Using the full 16K context window can add up to 11.7 GB, bringing total usage to 21.5 GB. 39 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run WhiteRabbitNeo 13B V1?
Q4_K_M · 9.8 GB49 devices with unified memory can run WhiteRabbitNeo 13B V1, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, iPad Pro M5 13" (16 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download WhiteRabbitNeo 13B V1
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does WhiteRabbitNeo 13B V1 need?
WhiteRabbitNeo 13B V1 requires 9.8 GB of VRAM at Q4_K_M, or 28.0 GB at BF16. Full 16K context adds up to 11.7 GB (21.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 13B × 4.8 bits ÷ 8 = 7.8 GB
KV Cache + Overhead ≈ 2 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 13.7 GB (at full 16K context)
VRAM usage by quantization
Q4_K_M9.8 GBQ4_K_M + full context21.5 GB- Can NVIDIA GeForce RTX 4090 run WhiteRabbitNeo 13B V1?
Yes, at Q8_0 (15.0 GB) or lower. Higher quantizations like BF16 (28.0 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for WhiteRabbitNeo 13B V1?
For WhiteRabbitNeo 13B V1, Q4_K_M (9.8 GB) offers the best balance of quality and VRAM usage. Q5_K_S (10.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 7.5 GB.
VRAM requirement by quantization
Q2_K7.5 GBQ3_K_L8.6 GBQ4_K_M ★9.8 GBQ5_K_S10.9 GBQ6_K12.7 GBBF1628.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run WhiteRabbitNeo 13B V1 on a Mac?
WhiteRabbitNeo 13B V1 requires at least 7.5 GB at Q2_K, 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 WhiteRabbitNeo 13B V1 locally?
Yes — WhiteRabbitNeo 13B V1 can run locally on consumer hardware. At Q4_K_M quantization it needs 9.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is WhiteRabbitNeo 13B V1?
At Q4_K_M, WhiteRabbitNeo 13B V1 can reach ~450 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~67 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 ÷ 9.8 × 0.65 = ~532 tok/s
Estimated speed at Q4_K_M (9.8 GB)
~532 tok/s~67 tok/s~532 tok/s~450 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of WhiteRabbitNeo 13B V1?
At Q4_K_M, the download is about 7.80 GB. The full-precision BF16 version is 26.00 GB. The smallest option (Q2_K) is 5.53 GB.
- Which GPUs can run WhiteRabbitNeo 13B V1?
39 consumer GPUs can run WhiteRabbitNeo 13B V1 at Q4_K_M (9.8 GB). Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 26 GPUs have plenty of headroom for comfortable inference.
- Which devices can run WhiteRabbitNeo 13B V1?
52 devices with unified memory can run WhiteRabbitNeo 13B V1 at Q4_K_M (9.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.