Ko PlatYi 6B — Hardware Requirements & GPU Compatibility
Chat
Ko PlatYi 6B is a 6B-parameter open language model from kyujinpy. It supports a context window of up to 2,048 tokens. At Q4_K_M it needs about 4.03 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 2K)Best on 24 GB (Q4_K_M · ~163 tok/s · 2K)Macs from 8 GB (Q4_K_M · ~18 tok/s)
CC BY-NC-SA 4.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Ko PlatYi 6B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve kyujinpy/Ko-PlatYi-6B --max-model-len 2048vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (8 GB headroom) · Q4_K_M
- Generation speed
- ~147 tok/s
- generation speed
- Cost per 1M output tokens
- $0.23
- per 1M output tokens
How Much VRAM Does Ko PlatYi 6B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.0 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 2K context · ~220 tok/s | |
| 3.4 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 2K context · ~195 tok/s | |
| 4.0 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 2K context · ~163 tok/s | |
| 4.7 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 2K context · ~139 tok/s | |
| 5.4 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 2K context · ~122 tok/s | |
| 6.4 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 2K context · ~102 tok/s | |
| 12.4 GB | — | 16-bit · full — Full half-precision — baseline for inference | Fits: 2K context · ~53 tok/s |
Selected Q4_K_M
4-bit medium quantization4.0GBat 2K context
- Weights
- 3.6 GB
- KV cache
- 0.1 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 20.0 GB free · ~163 tok/s
≥50 tok/s needs ≥310 GB/s · RTX 5090 ~289, RTX 3090 Ti ~163
Which Hardware Can Run Ko PlatYi 6B?
Q4_K_M · 4.0 GBKo PlatYi 6B (Q4_K_M) requires 4.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 6+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Ko PlatYi 6B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), MacBook Air 13" M3 (8 GB).
≤ 11 GB
≤ 11 GB tier →fits · 4.0 GB free · up to 2K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~123Simulate output on RTX 3080RTX 2080 Ti~99Simulate output on RTX 2080 TiRTX 3070 Ti~98Simulate output on RTX 3070 TiM3*8 GB~18Simulate output on iMac 24" M3 (8 GB)Orin Nano~17Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~12Simulate output on iPhone 1720 GB
fits · 16.0 GB free · up to 2K ctx
1 GPU
RX 7900 XT~119Simulate output on RX 7900 XT32–40 GB
fits · 28.0 GB free · up to 2K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~289Simulate output on RTX 5090M5 Max36 GB~80Simulate output on Mac Studio M5 Max (36 GB)M532 GB~27Simulate output on MacBook Air 13" M5 (32 GB)Orin~33Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~22Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
4| 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 |
| T5gemma 2B 2B Ul2Google | — | 6 GB | ~178 | same size |
| Yi 1.5 6B Chat01.AI | — | 4.2 GB | ~161 | same size |
Specifications
- Publisher
- kyujinpy
- Parameters
- 6B
- Architecture
- LlamaForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 78,464
- Release Date
- 2023-12-02
- License
- CC BY-NC-SA 4.0
Frequently Asked Questions
How much VRAM does Ko PlatYi 6B need?
Ko PlatYi 6B requires 4.0 GB of VRAM at Q4_K_M, or 12.4 GB at FP16.
VRAM = Weights + KV Cache + Overhead
Weights = 6B × 4.8 bits ÷ 8 = 3.6 GB
KV Cache + Overhead ≈ 0.4 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
What's the best quantization for Ko PlatYi 6B?
For Ko PlatYi 6B, Q4_K_M (4.0 GB) offers the best balance of quality and VRAM usage. Q5_K_M (4.7 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 3.0 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Ko PlatYi 6B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Ko PlatYi 6B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 4.0 GB of usable unified memory (RAM minus macOS overhead).
Can I run Ko PlatYi 6B locally?
Yes — Ko PlatYi 6B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Ko PlatYi 6B?
At Q4_K_M, Ko PlatYi 6B can reach ~1191 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~163 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 ÷ 4.03 × 0.65 = ~1290 tok/s
Estimated speed at Q4_K_M (4.0 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Ko PlatYi 6B?
At Q4_K_M, the download is about 3.60 GB. The full-precision FP16 version is 12.00 GB. The smallest option (Q2_K) is 2.55 GB.
Which GPUs can run Ko PlatYi 6B?
52 consumer GPUs can run Ko PlatYi 6B at Q4_K_M. 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 Ko PlatYi 6B?
163 devices with unified memory can run Ko PlatYi 6B at Q4_K_M (4.0 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.