LLMs · Alibaba
Qwen2 57B-A14B Instruct
- Parameters
- 57B (14.0B active)
- Architecture
- Mixture of experts
- Max context
- 32K tokens
- License
- apache-2.0
- Released
- 2024-06
How to run it
Quantized files · GGUF
Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.
huggingface.co/Qwen/Qwen2-57B-A14B-Instruct-GGUF (opens in a new tab)
ollama run hf.co/Qwen/Qwen2-57B-A14B-Instruct-GGUFOriginal weights · Hugging Face
Full-precision files from Alibaba, for fine-tuning, vLLM, Transformers.
huggingface.co/Qwen/Qwen2-57B-A14B-Instruct (opens in a new tab)
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 8K context | Total at 32K context | Download |
|---|---|---|---|---|---|
Q2_K |
Low | 23.0 GB | 24.0 GB | 25.4 GB | GGUF files (opens in a new tab) |
Q3_K_M |
Low | 28.1 GB | 29.2 GB | 30.6 GB | GGUF (opens in a new tab) |
Q4_K_M |
Good | 35.0 GB | 36.1 GB | 37.5 GB | GGUF (opens in a new tab) |
Q5_K_M |
High | 40.8 GB | 41.8 GB | 43.2 GB | GGUF (opens in a new tab) |
Q6_K |
High | 47.1 GB | 48.1 GB | 49.6 GB | GGUF (opens in a new tab) |
Q8_0 |
Very high | 60.9 GB | 61.9 GB | 63.3 GB | GGUF · part 1 of 2 (opens in a new tab) |
F16 |
Full | 115 GB | 116 GB | 117 GB | GGUF · part 1 of 3 (opens in a new tab) Original weights (opens in a new tab) |
Best hardware for Qwen2 57B-A14B Instruct
The least expensive GPU in our catalog that runs it without offloading is the Intel Arc Pro B70 (launch price $949) at Q3_K_M.
| Grade · points | Hardware | Quant | Memory | Speed | Fit |
|---|---|---|---|---|---|
| 77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 | NVIDIA RTX PRO 6000 Blackwell | Q8_0 | 66.7 GB / 96.0 GB | 40.0 tok/s | Runs well |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 18.9/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15 | NVIDIA GeForce RTX 5090 | Q3_K_M | 30.8 GB / 32.0 GB | 102 tok/s | Tight fit |
| 72 ptsGreat (A) · 72 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 15.0/15 | Apple M4 Max (64 GB) | Q4_K_M | 39.9 GB / 48.0 GB | 20.6 tok/s | Runs well |
| 70 ptsGood (B) · 70 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 9.2/15, Memory use 15.0/15 | Apple M1 Max (64 GB) | Q4_K_M | 39.9 GB / 48.0 GB | 15.1 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 10.8/15, Memory use 10.5/15 | Apple M4 Max (128 GB) | Q4_K_M | 43.8 GB / 96.0 GB | 20.6 tok/s | Runs well |
| 67 ptsGood (B) · 67 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 13.0/15, Memory use 7.6/15 | Apple M2 Ultra (192 GB) | Q4_K_M | 47.6 GB / 144 GB | 30.2 tok/s | Runs well |
| 66 ptsGood (B) · 66 of 100 points: Model quality 18.9/45, Memory fit 24.0/25, Speed 8.7/15, Memory use 15.0/15 | Apple M4 Pro (48 GB) | Q3_K_M | 32.1 GB / 36.0 GB | 13.3 tok/s | Tight fit |
| 65 ptsGood (B) · 65 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 13.2/15, Memory use 6.2/15 | Apple M3 Ultra (256 GB) | Q4_K_M | 51.4 GB / 192 GB | 30.9 tok/s | Runs well |
| 64 ptsGood (B) · 64 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 7.4/15, Memory use 10.5/15 | AMD Ryzen AI Max+ 395 (128 GB) | Q4_K_M | 43.8 GB / 96.0 GB | 9.7 tok/s | Runs well |
| 63 ptsGood (B) · 63 of 100 points: Model quality 21.4/45, Memory fit 25.0/25, Speed 8.2/15, Memory use 9.1/15 | NVIDIA GB10 (128 GB) | Q4_K_M | 45.3 GB / 115 GB | 12.0 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.