Qwen1.5 MoE A2.7B Chat on AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (64 GB)
Can the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (64 GB) run Qwen1.5 MoE A2.7B Chat?
Yes, it runs great
Runs great. At Q3_K_M it needs about 13.6 GB of 54.4 GB usable, with an estimated speed of 37.1 tok/s.
- Best quant
Q3_K_M- Generation speed
- 37.1 tok/s
- Prompt processing
- 161 tok/s
- First token (1K prompt)
- 6.4 s
- Largest safe context
- 8K
Download Qwen1.5 MoE A2.7B Chat
Original weights · Hugging Face
Full-precision files from Alibaba, for fine-tuning, vLLM, Transformers.
huggingface.co/Qwen/Qwen1.5-MoE-A2.7B-Chat (opens in a new tab)
How it’s rated
Match score
To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.
| Model quality | 9.1 / 45 | |
|---|---|---|
| Memory fit | 25.0 / 25 | |
| Speed | 14.4 / 15 | |
| Memory use | 5.8 / 15 | |
| Match score | 54.3 / 100 |
Every quantization on the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS (64 GB)
| Quant | Memory needed | Available | Speed | Runs | Quality | Download |
|---|---|---|---|---|---|---|
Q2_K | 12.3 GB | 54.4 GB | 45.8 tok/s | Runs great | 16Basic quality (D) · 16 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q3_K_M | 13.6 GB | 54.4 GB | 37.1 tok/s | Runs great | 20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q4_K_M | 15.3 GB | 54.4 GB | 29.4 tok/s | Runs well | 22Basic quality (D) · 22 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q5_K_M | 16.7 GB | 54.4 GB | 24.6 tok/s | Runs well | 23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q6_K | 18.3 GB | 54.4 GB | 20.9 tok/s | Runs well | 23Basic quality (D) · 23 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
Q8_0 | 21.7 GB | 54.4 GB | 15.6 tok/s | Runs well | 24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | All files (opens in a new tab) |
F16 | 35.2 GB | 54.4 GB | 7.4 tok/s | Slow | 24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Original weights (opens in a new tab) |
Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.
Other hardware that runs it
-
24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.
AMD Radeon RX 7900 XTX
-
24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.
Apple M4 Max (64 GB)
-
24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.
NVIDIA GeForce RTX 3090
-
24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.
NVIDIA GeForce RTX 4090
-
23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.
AMD Radeon RX 9070 XT
-
23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.
Apple M4 Pro (24 GB)
Quick answers
How much memory does Qwen1.5 MoE A2.7B Chat need on the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS 64GB?
At Q3_K_M it needs about 13.6 GB. The AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS 64GB has 54.4 GB usable.
How fast is Qwen1.5 MoE A2.7B Chat on the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS 64GB?
About 37.1 tok/s at Q3_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.
Which quantization of Qwen1.5 MoE A2.7B Chat should I use on the AMD Ryzen 7000 series (desktop, incl. PRO 7645 / 7745) NAS 64GB?
Q3_K_M. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.
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.