Kimi Linear Tiny Random — Hardware Requirements & GPU Compatibility
ChatFunctions
Kimi Linear Tiny Random is a 6M-parameter open language model from yujiepan in the Kimi family. At BF16 it needs about 0.31 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (BF16 · 32K)Best on 24 GB (BF16 · ~1461 tok/s · 32K)Macs from 32 GB (~239 tok/s)
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Kimi Linear Tiny Random
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
vllm serve yujiepan/kimi-linear-tiny-random --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 3060 12GB (11 GB headroom) · BF16
- Generation speed
- ~704 tok/s
- generation speed
- Cost per 1M output tokens
- $0.028
- per 1M output tokens
How Much VRAM Does Kimi Linear Tiny Random Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.3 GB | 0.3 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~1461 tok/s |
Selected BF16
Brain floating point 160.3GBat 16K context
- Weights
- 0.1 GB
- KV cache
- 0.0 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.7 GB free · ~1461 tok/s
≥50 tok/s needs ≥21 GB/s · RTX 5090 ~1979, RTX 3090 Ti ~1461
Which Hardware Can Run Kimi Linear Tiny Random?
BF16 · 0.3 GBKimi Linear Tiny Random (BF16) requires 0.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 176 devices with unified memory can run Kimi Linear Tiny Random, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
≤ 11 GB
≤ 11 GB tier →fits · 7.7 GB free · up to 32K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~1223Simulate output on RTX 3080RTX 2080 Ti~1058Simulate output on RTX 2080 TiRTX 3070 Ti~1049Simulate output on RTX 3070 TiM3*8 GB~211Simulate output on iMac 24" M3 (8 GB)Orin Nano~231Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~151Simulate output on iPhone 1720 GB
fits · 19.7 GB free · up to 32K ctx
1 GPU
RX 7900 XT~642Simulate output on RX 7900 XT32–40 GB
fits · 31.7 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~1979Simulate output on RTX 5090M5 Max36 GB~546Simulate output on Mac Studio M5 Max (36 GB)M532 GB~286Simulate output on MacBook Air 13" M5 (32 GB)Orin~437Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~281Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Alternatives to Kimi Linear Tiny Random
Kimi family · 5 models →Specifications
- Publisher
- yujiepan
- Family
- Kimi
- Parameters
- 6M
- Active parameters
- 0B per token
- Architecture
- KimiLinearForCausalLM
- Vocabulary Size
- 163,840
- Release Date
- 2025-11-04
Frequently Asked Questions
How much VRAM does Kimi Linear Tiny Random need?
Kimi Linear Tiny Random requires 0.3 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 6M × 16 bits ÷ 8 = 0 GB
KV Cache + Overhead ≈ 0.3 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.
VRAM usage by quantization
Can I run Kimi Linear Tiny Random on a Mac?
Yes — Mac Mini M1 (8 GB) and 155 other Macs can run Kimi Linear Tiny Random. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 0.3 GB of usable unified memory (RAM minus macOS overhead).
Can I run Kimi Linear Tiny Random locally?
Yes — Kimi Linear Tiny Random can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Kimi Linear Tiny Random?
At BF16, Kimi Linear Tiny Random can reach ~947 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~1461 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 → 0.3 GB active ÷ (8000 × 0.65) = 0.0516 ms, plus 5 layers × 0.055 ms = 0.2750 ms, so 1000 ÷ 0.3266 ms = ~3062 tok/s
Estimated speed at BF16 (0.3 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Kimi Linear Tiny Random?
At BF16, the download is about 0.01 GB.
Which GPUs can run Kimi Linear Tiny Random?
52 consumer GPUs can run Kimi Linear Tiny Random at BF16. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run Kimi Linear Tiny Random?
176 devices with unified memory can run Kimi Linear Tiny Random at BF16 (0.3 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.