Kimi Linear 48B A3B Instruct — Hardware Requirements & GPU Compatibility
Chat
Kimi Linear 48B A3B Instruct is a 49.1B-parameter open language model from Moonshot AI in the Kimi family. At BF16 it needs about 99.05 GB of VRAM — see which GPUs and Macs can run it below.
43.1K downloads
568 likesSpecifications
- Publisher
- Moonshot AI
- Family
- Kimi
- Parameters
- 49.1B
- Architecture
- KimiLinearForCausalLM
- Vocabulary Size
- 163,840
- Release Date
- 2025-10-30
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does Kimi Linear 48B A3B Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 99.0 GB | — | 98.25 GB | Brain floating point 16 — preferred for training |
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 Kimi Linear 48B A3B Instruct?
BF16 · 99.0 GBKimi Linear 48B A3B Instruct (BF16) requires 99.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 129+ GB is recommended. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Kimi Linear 48B A3B Instruct?
BF16 · 99.0 GB11 devices with unified memory can run Kimi Linear 48B A3B Instruct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Pro 16" M5 Max (128 GB).
Runs great
— Plenty of headroom
Frequently Asked Questions
- How much VRAM does Kimi Linear 48B A3B Instruct need?
Kimi Linear 48B A3B Instruct requires 99.0 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 49.1B × 16 bits ÷ 8 = 98.2 GB
KV Cache + Overhead ≈ 0.8 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF1699.0 GB- Can NVIDIA GeForce RTX 5090 run Kimi Linear 48B A3B Instruct?
No — Kimi Linear 48B A3B Instruct requires at least 99.0 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Kimi Linear 48B A3B Instruct on a Mac?
Kimi Linear 48B A3B Instruct requires at least 99.0 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 Kimi Linear 48B A3B Instruct locally?
Yes — Kimi Linear 48B A3B Instruct can run locally on consumer hardware. At BF16 quantization it needs 99.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Kimi Linear 48B A3B Instruct?
At BF16, Kimi Linear 48B A3B Instruct can reach ~44 tok/s on AMD Instinct MI350X. 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 ÷ 99.0 × 0.65 = ~53 tok/s
Estimated speed at BF16 (99.0 GB)
~53 tok/s~53 tok/s~44 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Kimi Linear 48B A3B Instruct?
At BF16, the download is about 98.25 GB.
- Which GPUs can run Kimi Linear 48B A3B Instruct?
No single consumer GPU has enough VRAM to run Kimi Linear 48B A3B Instruct at BF16 (99.0 GB). Multi-GPU or professional hardware is required.
- Which devices can run Kimi Linear 48B A3B Instruct?
18 devices with unified memory can run Kimi Linear 48B A3B Instruct at BF16 (99.0 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), 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.