LLMs · 01.AI
Yi 1.5 6B Chat
- Parameters
- 6.1B
- Architecture
- Dense
- Max context
- 4K tokens
- License
- apache-2.0
- Released
- 2024-05
How to run it
Quickest · Ollama
One command downloads a ready-to-run version and starts a chat.
ollama run yi:6b-chat-v1.5-q4_K_MQuantized files · GGUF
Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.
huggingface.co/bartowski/Yi-1.5-6B-Chat-GGUF (opens in a new tab)
ollama run hf.co/bartowski/Yi-1.5-6B-Chat-GGUFOriginal weights · Hugging Face
Full-precision files from 01.AI, for fine-tuning, vLLM, Transformers.
Memory needed
Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.
| Quantization | Quality | Weights | Total at 4K context | Download |
|---|---|---|---|---|
Q2_K |
Low | 2.4 GB | 3.3 GB | GGUF (opens in a new tab) |
Q3_K_M |
Low | 3.0 GB | 3.8 GB | GGUF (opens in a new tab) |
Q4_K_M |
Good | 3.7 GB | 4.6 GB | GGUF (opens in a new tab) |
Q5_K_M |
High | 4.3 GB | 5.2 GB | GGUF (opens in a new tab) |
Q6_K |
High | 5.0 GB | 5.8 GB | GGUF (opens in a new tab) |
Q8_0 |
Very high | 6.4 GB | 7.3 GB | GGUF (opens in a new tab) |
F16 |
Full | 12.1 GB | 13.0 GB | Original weights (opens in a new tab) |
Best hardware for Yi 1.5 6B Chat
The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at Q3_K_M.
| Grade · points | Hardware | Quant | Memory | Speed | Fit |
|---|---|---|---|---|---|
| 67 ptsGood (B) · 67 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | NVIDIA GeForce RTX 4070 SUPER | Q8_0 | 7.9 GB / 12.0 GB | 52.0 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 12.2/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | NVIDIA GeForce RTX 4060 | Q5_K_M | 5.6 GB / 8.0 GB | 45.5 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15 | NVIDIA GeForce RTX 3090 | F16 | 14.2 GB / 24.0 GB | 44.5 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.6/15 | NVIDIA GeForce RTX 4090 | F16 | 14.2 GB / 24.0 GB | 47.9 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 12.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.4/15 | Intel Arc B580 | Q6_K | 6.4 GB / 12.0 GB | 49.0 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 12.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.4/15 | NVIDIA GeForce RTX 3060 12GB | Q6_K | 6.4 GB / 12.0 GB | 50.6 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.7/15 | AMD Radeon RX 9070 XT | Q8_0 | 8.1 GB / 16.0 GB | 56.8 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.7/15 | NVIDIA GeForce RTX 4070 Ti SUPER | Q8_0 | 8.1 GB / 16.0 GB | 69.3 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.7/15 | NVIDIA GeForce RTX 4080 SUPER | Q8_0 | 8.1 GB / 16.0 GB | 75.9 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 12.6/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.7/15 | NVIDIA GeForce RTX 5060 Ti 16GB | Q8_0 | 8.1 GB / 16.0 GB | 46.2 tok/s | Runs well |
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.