Can Desktop PC · Ryzen 9 9950X (no GPU) · 64 GB DDR5 run Kolibri-1 (78B-A3.5B)?
64 GB RAM, no GPU · Kolibri-1 (78B-A3.5B) has 78.1B parameters (3.46B active per token).
Short answer
Yes, comfortable for chat; borderline for agentic coding.
Best quantization for chat: Q4_K_M (45 GB of weights) on llama.cpp (llama-server). Generation: 13–20 tok/s, leaving about 7.0 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 | Comfortable | Q4_K_M | 13–20 tok/s | ≈3 s | 8K | Details |
| Coding questionswith Continue | Acceptable | Q4_K_M | 12–20 tok/s | ≈20 s | 16K | Details |
| Coding in a repositorywith Aider | Acceptable | Q4_K_M | 11–19 tok/s | ≈55 s | 32K | Details |
| Agentic codingwith OpenCode | Borderline | Q4_K_M | 11–18 tok/s | ≈75 s | 32K | Details |
| Long documents (64K)with Open WebUI | Acceptable | Q4_K_M | 9–14 tok/s | ≈4 min | 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
Other models for Desktop PC · Ryzen 9 9950X (no GPU) · 64 GB DDR5
The best-rated models for chat on this machine.
- LFM2.5 24B-A2B20–35 tok/sExcellent
- MiniCPM5 2B20–35 tok/sExcellent
- Llama 3.2 3B Instruct16–25 tok/sExcellent
- Qwen3.6 35B-A3B11–18 tok/sComfortable
- Qwen3-Next 80B-A3B Instruct15–25 tok/sComfortable
- Gemma 4 26B-A4B10–17 tok/sComfortable
Cheapest machines for Kolibri-1 (78B-A3.5B)
Hardware rated comfortable or better for chat, lowest price first.
- Ryzen AI Max+ 395 mini PC / Framework Desktop · 64 GB$1,600 · 65–90 tok/sExcellent
- Ryzen AI Max+ 395 mini PC / Framework Desktop · 128 GB$2,000 · 40–55 tok/sExcellent
- Mac mini M4 Pro 64 GB$2,199 · 60–80 tok/sExcellent
- Mac Studio M1 Max 64 GB$2,399 · 80–110 tok/sExcellent
- Mac mini M5 Pro 64 GB$2,499 · 55–90 tok/sExcellent
- Mac Studio M2 Max 64 GB$2,599 · 85–110 tok/sExcellent
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.