Can Surface Laptop Ultra · RTX Spark N1X (20-core) · 128 GB run Qwen2.5-Coder 32B Instruct?
128 GB unified · 300 GB/s memory bandwidth · Qwen2.5-Coder 32B Instruct has 32.8B parameters.
Short answer
Yes, acceptable for chat; borderline for coding in a repository.
Best quantization for chat: Q5_K_M (22 GB of weights) on Ollama. Generation: 6–10 tok/s, leaving about 91 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 | Acceptable | Q5_K_M | 6–10 tok/s | under 1 s | 8K | Details |
| Coding questionswith Continue | Acceptable | Q4_K_M | 7–11 tok/s | ≈3 s | 16K | Details |
| Coding in a repositorywith Aider | Borderline | Q5_K_M | 5–9 tok/s | ≈10 s | 32K | Details |
| Agentic codingwith OpenCode | Borderline | Q6_K | 4.5–8 tok/s | ≈15 s | 32K | Details |
| Long documents (64K)with Open WebUI | Acceptable | Q5_K_M | 4.7–8 tok/s | ≈25 s | 32K | 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 Q5_K_M build with a 32K context. Ollama and llama.cpp download the file straight from Hugging Face.
ollama run hf.co/unsloth/Qwen2.5-Coder-32B-Instruct-GGUF:Q5_K_M
Downloads 23.26 GB (Q5_K_M). Ollama's default context is small: set OLLAMA_CONTEXT_LENGTH=32768 before `ollama serve` for long prompts.
Other models for Surface Laptop Ultra · RTX Spark N1X (20-core) · 128 GB
The best-rated models for chat on this machine.
- gpt-oss-120b40–65 tok/sExcellent
- Qwen3.6 35B-A3B45–75 tok/sExcellent
- Qwen3-Next 80B-A3B Instruct45–75 tok/sExcellent
- Gemma 4 26B-A4B35–60 tok/sExcellent
- LFM2.5 24B-A2B85–150 tok/sExcellent
- Qwen3.5 35B-A3B45–75 tok/sExcellent
Cheapest machines for Qwen2.5-Coder 32B Instruct
Hardware rated comfortable or better for chat, lowest price first.
- Desktop PC · GeForce RTX 3090 · 32 GB RAM$1,700 · 25–35 tok/sExcellent
- Desktop PC · Radeon RX 7900 XTX · 32 GB RAM$1,800 · 30–40 tok/sExcellent
- Desktop PC · GeForce RTX 3090 · 64 GB RAM$1,828 · 25–35 tok/sExcellent
- Desktop PC · Radeon RX 7900 XTX · 64 GB RAM$1,928 · 30–40 tok/sExcellent
- Mac Studio M1 Max 32 GB$1,999 · 12–17 tok/sComfortable
- Mac Studio M2 Max 32 GB$2,199 · 12–17 tok/sComfortable
Same chip, other memory: 24 GB
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.