Can Desktop PC · 2× GeForce RTX 3090 (48 GB) · 128 GB RAM run Qwen3-Next 80B-A3B Instruct?
48 GB VRAM + 128 GB RAM · 936 GB/s memory bandwidth · Qwen3-Next 80B-A3B Instruct has 81.3B parameters (3B active per token).
Short answer
Yes, excellent for chat and acceptable or better for every workload we test.
Best quantization for chat: Q3_K_M (37 GB of weights) on Ollama. Generation: 230–380 tok/s, leaving about 8.7 GB free for your other apps.
How it rates for each workload
Same model and machine, different jobs. Agents and long documents send far bigger prompts than chat, so they need much more speed and memory.
| Workload | Verdict | Quant | Generation | First reply | Context | |
|---|---|---|---|---|---|---|
| Chatwith Open WebUI | Excellent | Q3_K_M | 230–380 tok/s | under 1 s | 8K | Details |
| Coding questionswith Continue | Comfortable | Q3_K_M | 210–360 tok/s | ≈1 s | 16K | Details |
| Coding in a repositorywith Aider | Acceptable | Q3_K_M | 180–310 tok/s | ≈2 s | 32K | Details |
| Agentic codingwith OpenCode | Acceptable | Q3_K_M | 170–290 tok/s | ≈3 s | 32K | Details |
| Long documents (64K)with Open WebUI | Excellent | Q3_K_M | 130–210 tok/s | ≈9 s | 64K | Details |
Speeds are bandwidth-based estimates; no direct benchmark exists for this pair. “First reply” is the time to read the workload’s opening prompt. How we calculate
Get it running
Copy-paste commands for the Q3_K_M build with a 64K context. Ollama and llama.cpp download the file straight from Hugging Face.
ollama run hf.co/unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF:Q3_K_M
Downloads 38.3 GB (Q3_K_M). Ollama's default context is small: set OLLAMA_CONTEXT_LENGTH=65536 before `ollama serve` for long prompts.
Other models for Desktop PC · 2× GeForce RTX 3090 (48 GB) · 128 GB RAM
The best-rated models for chat on this machine.
- Recursive Flint (40B-A2.5B)250–410 tok/sExcellent
- Qwen3.6 35B-A3B140–230 tok/sExcellent
- Gemma 4 26B-A4B110–180 tok/sExcellent
- Qwen3.5 35B-A3B140–230 tok/sExcellent
- LFM2.5 24B-A2B270–450 tok/sExcellent
- gpt-oss-20b160–270 tok/sExcellent
Cheapest machines for Qwen3-Next 80B-A3B Instruct
Hardware rated comfortable or better for chat, lowest price first.
- Desktop PC · Ryzen 9 9950X (no GPU) · 64 GB DDR5$1,400 · 15–25 tok/sComfortable
- Ryzen AI Max+ 395 mini PC / Framework Desktop · 64 GB$1,600 · 80–110 tok/sComfortable
- Ryzen AI Max+ 395 mini PC / Framework Desktop · 128 GB$2,000 · 55–75 tok/sExcellent
- Mac mini M4 Pro 64 GB$2,199 · 70–100 tok/sExcellent
- Mac Studio M1 Max 64 GB$2,399 · 100–140 tok/sExcellent
- Mac mini M5 Pro 64 GB$2,499 · 65–110 tok/sExcellent
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.