Which GPUs and Macs run Recursive Flint?
Key facts
Recursive Flint needs about 24.5 GB of graphics memory. It runs on 3 of the 10 graphics card setups on this page, such as the RTX 5090. On a single 24 GB card it fits at 3-bit UD-Q3_K_XL (18.49 GB measured weights, 19.56 GB total estimate at 8,192 context, about 3.8 GB spare).
About 24.5 GB at Q4_K_M, our estimate. Checked . ggml-org Q4_K_M GGUF (official ggml-org repo).
Try Recursive Flint free in your browser, no login, no install
The cheapest machine on our list that runs it: Mac mini M4 Pro 64GB, about $2,116€1,890 (used).
Our price is for a used Mac. These shops mostly sell new ones, so their price can be higher.
EU shops · Shown to visitors in Europe.
US shops · Shown to visitors outside Europe.
If you buy through these links we may earn a commission. It doesn't change our ranking. How shop links work
As an Amazon Associate I earn from qualifying purchases.
Als Amazon-Partner verdiene ich an qualifizierten Verkäufen.
Als Amazon-Partner verdien ik aan in aanmerking komende aankopen.
We never pass off an estimate as a benchmark. Commissions never change which hardware we recommend. How we calculate
We don't give a speed for this model yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.
LIVE IN BROWSER · $0 · NO LOGIN
Test Recursive Flint (40B MoE) free in your browser before downloading 23.39 GB
Open full 8-model playground ↗You can test Recursive Flint (recursive/flint-v1.0:free, 39.79B total parameters with 2.5B active per token; 262,144 max context; Apache-2.0, our reading of the licence, not legal advice) free in your browser with no login and 0 GB of local VRAM. Send one coding or reasoning prompt in the box below or open the full side-by-side chat at https://localllmrig.com/ to compare Recursive Flint against Gemma 4 31B, Gemma 4 26B A4B, and Laguna S 2.1 before downloading the local GGUF (24.46 GB total estimate at Q4_K_M = 23.39 GB measured weights + 0.27 GB KV cache at 8,192 tokens + 0.80 GB overhead, or 19.56 GB total at UD-Q3_K_XL to fit a single 24 GB GPU).
Test Recursive Flint vs 9 other free open models on localLLMrig →https://localllmrig.com/can-i-run/flint
Click a starter prompt below or type your own question to watch Recursive Flint stream side by side against Gemma 4 31B right on this page:
Get a 1-line alert when a faster quant for Recursive Flint drops — or when GPUs that run it drop >10%
Get a 1-line alert when a new open-weight model fits 32 GB VRAM (24.5 GB at Q4 for Recursive Flint) or when used RTX 3090 / 4090 & Mac Studio prices drop >10% — weekly, zero spam.
Which graphics cards run it
Seven popular graphics cards and two PCs with two cards each, at the standard quality (Q4). Click one for the full answer: memory, speed and price.
Runs well3
The whole model fits in the graphics memory.
Doesn't fit7
Not enough graphics memory: it needs about 24.5 GB. In a PC with enough normal memory it runs slowly: Budget PC with RTX 3060 12GB, about $1,310€1,361 (with a used graphics card).
- RTX 3060 12GBhas 12 GB
- RTX 4060 Ti 16GBhas 16 GB
- RTX 3090has 24 GB
- RTX 4090has 24 GB
- RTX 5080has 16 GB
- RX 9060 XT 16GBhas 16 GB
- RX 7900 XTXhas 24 GB
Which Macs and mini PCs run it
Macs and mini PCs from the picker, at the standard quality (Q4). A Mac shares its memory with the rest of the computer. Each name opens that machine's page.
Runs well10
The whole model fits in the memory the graphics can use.
Doesn't fit2
Not enough shared memory: it needs about 24.5 GB.
- Mac mini M4 16GBhas 16 GB
- Mac mini M6 32GBhas 32 GB
Cheapest hardware for each size
From all 43 graphics cards, PCs and Macs on our list. "Runs slowly" means part of the model runs from normal memory: cheaper, but much slower. A smaller download needs less memory and answers a little less well.
- Standard quality (Q4_K_M)Mac mini M4 Pro 64GB, about $2,116€1,890 (used)
- Standard quality (Q4_K_M), runs slowlyBudget PC with RTX 3060 12GB, about $1,310€1,361 (with a used graphics card)
- Smallest download (UD-IQ1_M)Radeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list)
- Smallest download (UD-IQ1_M), runs slowlyBudget PC with RTX 3060 12GB, about $1,310€1,361 (with a used graphics card)
Prices excl. shipping unless marked. Euro prices incl. VAT where the seller charges it. Dollar prices are converted from our euro prices without the 21% EU VAT, before US sales tax.
Prices moved: see Building a local LLM rig in the RAMageddon.
About Recursive Flint
MoE 35B-A3B vs dense 27B on 24 GB: Qwen3.6-35B-A3B vs Qwen3.8-27B.
39.79B total, 2.5B active. Parameter count is the published figure. More parameters usually means a smarter model that needs more memory.
- Licence:
- Apache-2.0 source
- Longest conversation:
- about 393 pages of text (262,144 tokens)
- Input:
- text
- Released:
- source
Sources and method
Recursive's coding model for agents that read code, fix bugs and write tests, under Apache 2.0. Only about 2.5B of its 40B parameters are used per word, so it does far less work per word than a dense 40B model. The 4-bit downloads are about 22 to 26 GB before any conversation memory.
Recursive-reported (announcement, not a measurement on this site). With Recursive's own inference engine, Flint generates more than 125 tokens per second on an M4 Pro MacBook Pro and more than 150 tokens per second on a 64GB NVIDIA RTX Spark at short contexts. Source: https://recursive.com/updates/introducing-recursive-flint
Ran Recursive Flint on your own hardware? Send us your llama-bench result.
Conversation memory for Recursive Flint, our estimate: 35 of 49 layers keep a 513-token sliding window and 14 layers cache the full context. At 8,192 tokens that cache is about 0.27 GB, at 32,768 tokens about 0.98 GB, at 131,072 tokens about 3.79 GB, and at 262,144 tokens about 7.55 GB. llama.cpp needs a build that includes Flint (b11803 or newer; leave --swa-full unset). Ollama: ollama run flint.
Memory at each quality level
Each download of Recursive Flint is a different size. The total adds the file, the memory a conversation of about 12 pages of text (8,192 tokens) takes, and 0.8 GB of working space. A measured file size is labelled; the rest is our estimate. The last column is the cheapest machine that holds the total.
Swipe the table sideways to see every column, up to the cheapest machine.
| Quality (file) | File size | Conversation | Working space | Total | Cheapest machine that holds it |
|---|---|---|---|---|---|
| BF16 | 79.63 GBmeasured GGUF | 0.3 GB | 0.8 GB | 80.7 GB | Mac Studio M4 Max 128GB, $3,683€3,290 (used), price unverified |
| Q8_0 | 42.35 GBmeasured GGUF | 0.3 GB | 0.8 GB | 43.4 GB | Mac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified |
| UD-Q6_K_XL | 36.32 GBmeasured GGUF | 0.3 GB | 0.8 GB | 37.4 GB | Mac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified |
| Q6_K | 35.20 GBmeasured GGUF | 0.3 GB | 0.8 GB | 36.3 GB | Mac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified |
| Q5_K_M | 30.81 GBmeasured GGUF | 0.3 GB | 0.8 GB | 31.9 GB | Mac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified |
| INT4-Q4_1 | 25.99 GBmeasured GGUF | 0.3 GB | 0.8 GB | 27.1 GB | Mac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified |
| UD-Q4_K_XL | 25.05 GBmeasured GGUF | 0.3 GB | 0.8 GB | 26.1 GB | Mac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified |
| Q4_K_M | 23.39 GBmeasured GGUF | 0.3 GB | 0.8 GB | 24.5 GB | Mac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified |
| NVFP4 | 22.86 GBmeasured GGUF | 0.3 GB | 0.8 GB | 23.9 GB | Mac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified |
| IQ4_XS | 22.45 GBmeasured GGUF | 0.3 GB | 0.8 GB | 23.5 GB | Mac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified |
| UD-Q3_K_XL | 18.49 GBmeasured GGUF | 0.3 GB | 0.8 GB | 19.6 GB | GeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings) |
| UD-IQ3_XXS | 14.54 GBmeasured GGUF | 0.3 GB | 0.8 GB | 15.6 GB | GeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings) |
| UD-Q2_K_XL | 13.56 GBmeasured GGUF | 0.3 GB | 0.8 GB | 14.6 GB | Radeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list) |
| UD-IQ1_M | 11.35 GBmeasured GGUF | 0.3 GB | 0.8 GB | 12.4 GB | Radeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list) |
speed: not estimated for MoE yet.
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate
Questions
- Where can I test Recursive Flint online for free before downloading 23.39 GB?
- You can test Recursive Flint (recursive/flint-v1.0:free), 39.79B total, 2.5B active, live in your browser for free at https://localllmrig.com/ or from https://localllmrig.com/can-i-run/flint, with no account and no graphics card. It is ticked by default on the home page. In Choose LLMs under Hardware $1,500–5,000, tick it alongside other free models, such as Gemma 4 31B, Gemma 4 26B A4B, NVIDIA Nemotron 3.5 Lightning, NVIDIA Nemotron 3.5 Super VL, and Laguna S 2.1, and compare code and reasoning on your own prompts (5 free questions every 10 minutes).
- Can Recursive Flint run on a 24 GB or 16 GB GPU?
- Q4_K_M (23.39 GB measured GGUF, 24.5 GB total estimate) at 8,192 tokens is 1.1 GB over a 24 GB card's 23.4 GB usable memory. The standard file fits 3 of the 10 graphics-card setups on https://localllmrig.com/can-i-run/flint: GeForce RTX 5090 32GB (€7,367 / $6,816); Dual RTX 3090, 128 GB RAM (€5,452 / $5,528, price unverified); Dual RTX 4090, 128 GB RAM (€7,330 / $7,631, price unverified). IQ4_XS (22.45 GB measured GGUF, 23.5 GB total estimate) is still 0.1 GB over a 24 GB card. UD-Q3_K_XL (18.49 GB measured GGUF, 19.6 GB total estimate) fits a single 24 GB card such as GeForce RTX 3090 24GB (€1,246 / $1,395), with 3.8 GB to spare. On a 16 GB card (15.4 GB usable), UD-Q2_K_XL (13.56 GB measured GGUF, 14.6 GB total estimate) fits, and so does UD-IQ1_M (11.35 GB measured GGUF, 12.4 GB total estimate).
- How does Recursive Flint keep its 262,144-token context window so light in memory?
- Recursive Flint has 49 layers (4 key-value heads, head size 128). 35 of those layers use a 513-token sliding window, and 14 layers keep the full context. Conversation memory is 0.27 GB at 8,192 tokens (0.3 GB rounded) and 7.55 GB across the full 262,144-token context (about 393 pages), our estimate. The same figures are on https://localllmrig.com/can-i-run/flint.
- Which llama.cpp version or Ollama command is required to run Recursive Flint locally?
- llama.cpp needs a build that includes Flint (b11803 or newer; leave --swa-full unset). Ollama: ollama run flint. The measured Q4_K_M file in this catalog is 23.39 GB. A 24 GB card holds UD-Q3_K_XL (18.49 GB measured GGUF, 19.6 GB total estimate); the standard file needs 32 GB of graphics memory or a Mac that leaves at least 24.5 GB usable.
- Which Macs, Ryzen AI Max+ 395 mini PCs, or DGX Spark machines run Recursive Flint best?
- At Q4_K_M (23.39 GB measured GGUF, 24.5 GB total estimate), a 32 GB Mac leaves about 21.3 GB usable, which is 3.1 GB short of the standard file. These measured files do fit Mac mini M6 32GB (21.3 GB usable, €1,530 / $1,416, price unverified): UD-Q3_K_XL (18.49 GB measured GGUF, 19.6 GB total estimate), UD-IQ3_XXS (14.54 GB measured GGUF, 15.6 GB total estimate), UD-Q2_K_XL (13.56 GB measured GGUF, 14.6 GB total estimate), UD-IQ1_M (11.35 GB measured GGUF, 12.4 GB total estimate). Complete machines on https://localllmrig.com/can-i-run/flint that hold the standard file, cheapest first: Mac mini M4 Pro 64GB (48.0 GB usable, €1,890 / $2,116, price unverified); GMKtec EVO-X2 (Ryzen AI Max+ 395) 64GB (48.0 GB usable, €2,199 / $2,035); Mac Studio M5 Max 36GB (27.0 GB usable, €3,029 / $2,802); Mac mini M5 Pro 64GB (48.0 GB usable, €3,200 / $2,961, price unverified); GMKtec EVO-X2 (Ryzen AI Max+ 395) 128GB (96.0 GB usable, €3,800 / $3,516); GEEKOM A9 Mega (Ryzen AI Max+ 395) 128GB (96.0 GB usable, €3,999 / $3,700); Beelink GTR9 Pro (Ryzen AI Max+ 395) 128GB (96.0 GB usable, €4,619 / $4,274); Mac Studio M5 Max 128GB (96.0 GB usable, €6,000 / $5,551, price unverified); Mac Studio M5 Ultra 96GB (72.0 GB usable, €6,649 / $6,152); Mac Studio M5 Ultra 256GB (192.0 GB usable, €12,500 / $11,565, price unverified). Larger files: Q5_K_M (30.81 GB measured GGUF, 31.9 GB total estimate) on Mac mini M4 Pro 64GB (48.0 GB usable); Q6_K (35.2 GB measured GGUF, 36.3 GB total estimate) on Mac mini M4 Pro 64GB (48.0 GB usable); Q8_0 (42.35 GB measured GGUF, 43.4 GB total estimate) on Mac mini M4 Pro 64GB (48.0 GB usable); BF16 (79.63 GB measured GGUF, 80.7 GB total estimate) on GMKtec EVO-X2 (Ryzen AI Max+ 395) 128GB (96.0 GB usable). We don't give a speed for this mixture-of-experts model yet.
- How fast does Recursive Flint generate tokens in real hardware benchmarks versus our formula?
- We don't give a speed for this model yet. This model only uses part of itself for each word (2.5B active of 39.79B total, a mixture of experts), and our speed estimate does not handle that yet. Recursive-reported (announcement, not a measurement on this site). With Recursive's own inference engine, Flint generates more than 125 tokens per second on an M4 Pro MacBook Pro and more than 150 tokens per second on a 64GB NVIDIA RTX Spark at short contexts. Source: https://recursive.com/updates/introducing-recursive-flint. An external write-up we did not run (InferenceKey) reports about 210 tokens per second on an RTX 5090 at 64K context and about 167 on an RTX 4090 at 16K, and says 32K ran out of memory on the 4090. Those figures are community measurements, not a localLLMrig measurement. The hardware table is on https://localllmrig.com/can-i-run/flint.
- How do Recursive Flint, Llama 3.3 70B and DeepSeek R1 Distill 70B compare with Claude and GPT?
- Want to see how local open models (Recursive Flint, Llama 3.3 70B, DeepSeek R1 Distill 70B) stack up against Claude Sonnet 5.5 and GPT-6.1 Sol before buying hardware? Run them side by side at https://localllmrig.com/ and read https://localllmrig.com/guides/compare-claude-and-gpt-with-local-llms.
- Can I try Recursive Flint online for free?
- Yes. Recursive Flint is on the free chat on the home page. Pick it there, ask a question, and read the answer in your browser. No login and no install.
- Do I need a GPU to test it?
- No. The free chat runs in your browser. It does not download the model and it does not use a graphics card on your computer. A graphics card only matters if you run the model yourself.
- Do I need an account to try Recursive Flint?
- No. The free chat needs no account and no login.