Can Desktop PC · Intel Arc Pro B60 24GB · 64 GB RAM run Recursive Flint (40B-A2.5B)?
24 GB VRAM + 64 GB RAM · 456 GB/s memory bandwidth · Recursive Flint (40B-A2.5B) has 39.8B parameters (2.5B active per token).
Short answer
Yes, excellent for chat; borderline for 64K-token documents.
Best quantization for chat: MXFP4 (20 GB of weights) on LM Studio. Generation: 95–160 tok/s, leaving about 2.0 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 | Excellent | MXFP4 | 95–160 tok/s | ≈1 s | 8K | Details |
| Coding questionswith Continue | Excellent | MXFP4 | 85–150 tok/s | ≈6 s | 16K | Details |
| Coding in a repositorywith Aider | Comfortable | MXFP4 | 70–120 tok/s | ≈20 s | 32K | Details |
| Agentic codingwith OpenCode | Comfortable | MXFP4 | 65–110 tok/s | ≈25 s | 32K | Details |
| Long documents (64K)with Open WebUI | Borderline | MXFP4 | 45–75 tok/s | ≈80 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
Other models for Desktop PC · Intel Arc Pro B60 24GB · 64 GB RAM
The best-rated models for chat on this machine.
- Qwen3.6 35B-A3B70–120 tok/sExcellent
- Gemma 4 26B-A4B45–80 tok/sExcellent
- LFM2.5 24B-A2B100–170 tok/sExcellent
- gpt-oss-20b60–100 tok/sExcellent
- Qwen3.5 35B-A3B70–120 tok/sExcellent
- GLM-4.7-Flash (30B-A3B)70–120 tok/sExcellent
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 · Ryzen 9 9950X (no GPU) · 64 GB DDR5$1,400 · 20–35 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
- Mac mini M2 Pro 32 GB$1,699 · 65–90 tok/sExcellent
- Mac mini M6 32 GB$1,699 · 45–75 tok/sExcellent
Same chip, other memory: 32 GB
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.