Recursive Flint runs at 92 tok/s (92.36 as recorded) on a 48 GB M5 Pro, a community run reported by github.com (llama.cpp, Q4_1, 512-token coding answers, median of 5 at T 1.0). It needs about 20 GB of unified memory. It is Recursive's 39.8B mixture-of-experts model (2.5B active), released under the Apache 2.0 licence.
Want to run Recursive Flint faster — or step up to bigger models? Find your Mac →This is a community run: a real run, reported by its source and linked below. The index records it as given and never adjusts it.
| Metric | Value |
|---|---|
| Tokens per second | community92 tok/s |
| Provenance | community run · github.com |
| Quantization | Q4_1 |
| Engine | llama.cpp |
| Context | 512-token coding answers, median of 5 at T 1.0 |
| Figure dated | 2026-10-22 |
| Minimum RAM | 20 GB |
| Parameters | 39.8B MoE (2.5B active) |
| Chip bandwidth | 307 GB/s |
Each row as the index holds it, with its source. “Mac RAM” is the memory of the Mac a run used, not the model’s requirement (20 GB). The headline figure follows the reference rule: the lower-median measured plain-decode run at 5 bits or fewer (a run whose quant was not stated counts only when no stated-quant run qualifies), else the estimate; a run marked “not used to anchor estimates” is listed here but never becomes the headline.
| Speed | Quant | Engine | Mac RAM | Context | Source | Note |
|---|---|---|---|---|---|---|
| community115 tok/s | 4-bit | Ollama | 64 GB | 18-token prompt, 1,075 generated | x.com | Mac mini. Ollama --verbose eval rate 115.33; the post says a 4-bit build but not which tag. Its 87 tok/s after a 20K-token prompt is a long-context figure, not this row. |
| community92.36 tok/s | Q4_1 | llama.cpp | 48 GB | 512-token coding answers, median of 5 at T 1.0 | github.com | MacBook Pro, 20-core GPU. llama.cpp b11804, Recursive's Q4_1 GGUF; greedy 92.84; no GPU contention; a single harness run. Run by the Kapitsa engine's developers with their own harness. |
| community80.7 tok/s | oQ4e | MLX | 48 GB | 1k | omlx.ai | 20-core GPU. oMLX v0.7.2, MTP/DFlash off; Flint-oQ4e; 22.2 GB peak. |
Ollama — install it (brew install ollama or the app from ollama.com), then pull the model by its tag, checked on ollama.com on 2026-10-24:
MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:
Downloads: Ollama page → · model card →
The 92 tok/s figure above came from llama.cpp at Q4_1; other runtimes and quants run at different speeds.
Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.
Recursive's Apache 2.0 coding-agent MoE (21 Oct 2026): 39.8B total, ~2.5B active, 262K context, text only, always reasons. Its card reports SWE-bench Verified 74.2 and Terminal-Bench 2.1 54.9 (its SWE-bench Pro v2 89.7 is an internal mini-swe-agent run, not comparable to SEAL's); the index's capability figure is estimated from these vendor coding benchmarks only. Stock llama.cpp b11803+, Ollama (flint:40b) and LM Studio run it, though llama.cpp's expert-scaling workaround costs 10–30% for now and issue #31000 (NVFP4 tool calls) is open. A ~18 GB 3-bit build fits a 24 GB Mac; community llama.cpp runs measured 92.4 tok/s on an M5 Pro and 79.6 on an M4 Pro (Q4_1).
Apache 2.0 licence · 39.8B MoE · 262K context · LLMCheck capability 37/50 · see its leaderboard rank →
Recursive Flint needs about 20 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:
As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.
See how Recursive Flint stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard