Can Desktop PC · Ryzen 9 9950X (no GPU) · 64 GB DDR5 run Recursive Flint (40B-A2.5B)?
64 GB RAM, no GPU · Recursive Flint (40B-A2.5B) has 39.8B parameters (2.5B active per token).
Short answer
Yes, excellent for chat and acceptable or better for every workload we test.
Best quantization for chat: MXFP4 (20 GB of weights) on llama.cpp (llama-server). Generation: 20–35 tok/s, leaving about 32 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 | MXFP4 | 20–35 tok/s | ≈2 s | 8K | Details |
| Coding questionswith Continue | Comfortable | MXFP4 | 18–30 tok/s | ≈15 s | 16K | Details |
| Coding in a repositorywith Aider | Acceptable | MXFP4 | 15–25 tok/s | ≈40 s | 32K | Details |
| Agentic codingwith OpenCode | Acceptable | MXFP4 | 14–25 tok/s | ≈55 s | 32K | Details |
| Long documents (64K)with Open WebUI | Acceptable | MXFP4 | 10–16 tok/s | ≈3 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 Recursive Flint (40B-A2.5B)
Hardware rated comfortable or better for chat, lowest price first.
- Mac mini M4 32 GB$1,399 · 40–55 tok/sExcellent
- Desktop PC · Intel Arc Pro B60 24GB · 32 GB RAM$1,500 · 95–160 tok/sExcellent
- Ryzen AI Max+ 395 mini PC / Framework Desktop · 64 GB$1,600 · 100–140 tok/sExcellent
- Desktop PC · Intel Arc Pro B60 24GB · 64 GB RAM$1,628 · 95–160 tok/sExcellent
- Mac mini M2 Pro 32 GB$1,699 · 65–90 tok/sExcellent
- Mac mini M6 32 GB$1,699 · 45–75 tok/sExcellent
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.