Polyglot Ko 1.3B — Hardware Requirements & GPU Compatibility
Chat
Polyglot Ko 1.3B is a 1.4B-parameter open language model from EleutherAI. It supports a context window of up to 2,048 tokens. At Q4_K_M it needs about 0.95 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 · ~690 tok/s · 2K)Macs from 8 GB (Q4_K_M · ~76 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Polyglot Ko 1.3B
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 EleutherAI/polyglot-ko-1.3b --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) (11 GB headroom) · Q4_K_M
- Generation speed
- ~624 tok/s
- generation speed
- Cost per 1M output tokens
- $0.054
- per 1M output tokens
How Much VRAM Does Polyglot Ko 1.3B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.7 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 2K context · ~978 tok/s | |
| 0.8 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 2K context · ~851 tok/s | |
| 0.9 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 2K context · ~690 tok/s | |
| 1.1 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 2K context · ~585 tok/s | |
| 1.3 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 2K context · ~504 tok/s | |
| 1.6 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 2K context · ~415 tok/s | |
| 3.1 GB | — | 16-bit · full — Full half-precision — baseline for inference | Fits: 2K context · ~208 tok/s |
Selected Q4_K_M
4-bit medium quantization1.0GBat 2K context
- Weights
- 0.4 GB
- KV cache
- 0.2 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 23.1 GB free · ~690 tok/s
≥50 tok/s needs ≥73 GB/s · RTX 5090 ~1226, RTX 3090 Ti ~690
Which Hardware Can Run Polyglot Ko 1.3B?
Q4_K_M · 0.9 GBPolyglot Ko 1.3B (Q4_K_M) requires 0.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ 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 Polyglot Ko 1.3B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 7.0 GB free · up to 2K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~520Simulate output on RTX 3080RTX 2080 Ti~422Simulate output on RTX 2080 TiRTX 3070 Ti~416Simulate output on RTX 3070 TiM3*8 GB~76Simulate output on iMac 24" M3 (8 GB)Orin Nano~70Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~50Simulate output on iPhone 1720 GB
fits · 19.1 GB free · up to 2K ctx
1 GPU
RX 7900 XT~505Simulate output on RX 7900 XT32–40 GB
fits · 31.1 GB free · up to 2K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~1226Simulate output on RTX 5090M5 Max36 GB~339Simulate output on Mac Studio M5 Max (36 GB)M532 GB~113Simulate output on MacBook Air 13" M5 (32 GB)Orin~140Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~92Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Inkling Small DSpark PreviewRadixArk | — | 1.5 GB | ~555 | same size |
| Qwen Base Invoicev1.01 1.5BLaaP-ai | — | 1.7 GB | ~512 | same size |
| OLMo 2 0425 1B InstructAllen AI | — | 1.7 GB | ~449 | same size |
| OpenMath Nemotron 1.5BNVIDIA | — | 1.7 GB | ~512 | same size |
| Granite 3.0 1B A400m InstructIBM | — | 1.3 GB | ~524 | same size |
| Qwen2.5 1.5B InstructAlibaba | — | 1.7 GB | ~512 | same size |
Specifications
- Publisher
- EleutherAI
- Parameters
- 1.4B
- Architecture
- GPTNeoXForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 30,080
- Release Date
- 2022-09-15
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Polyglot Ko 1.3B need?
Polyglot Ko 1.3B requires 0.9 GB of VRAM at Q4_K_M, or 3.1 GB at FP16.
VRAM = Weights + KV Cache + Overhead
Weights = 1.4B × 4.8 bits ÷ 8 = 0.9 GB
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 Polyglot Ko 1.3B?
For Polyglot Ko 1.3B, Q4_K_M (0.9 GB) offers the best balance of quality and VRAM usage. Q5_K_M (1.1 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.7 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Polyglot Ko 1.3B on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run Polyglot Ko 1.3B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run Polyglot Ko 1.3B locally?
Yes — Polyglot Ko 1.3B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Polyglot Ko 1.3B?
At Q4_K_M, Polyglot Ko 1.3B can reach ~5053 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~690 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 ÷ 0.95 × 0.65 = ~5474 tok/s
Estimated speed at Q4_K_M (0.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Polyglot Ko 1.3B?
At Q4_K_M, the download is about 0.86 GB. The full-precision FP16 version is 2.86 GB. The smallest option (Q2_K) is 0.61 GB.
Which GPUs can run Polyglot Ko 1.3B?
52 consumer GPUs can run Polyglot Ko 1.3B 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 Polyglot Ko 1.3B?
163 devices with unified memory can run Polyglot Ko 1.3B at Q4_K_M (0.9 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.