Can I run Recursive Flint on an RX 7900 XTX?
Key facts
Not at 4-bit Q4_K_M, which needs about 24.5 GB (24.46 GB estimate) while an RX 7900 XTX leaves about 23.4 GB usable out of 24 GB. It fits on a single an RX 7900 XTX at 3-bit UD-Q3_K_XL (unsloth/flint-GGUF, 18.49 GB measured weights, 19.56 GB total estimate at 8,192 context, leaving about 3.8 GB spare).
It needs about 24.5 GB at standard quality (estimate). Checked . ggml-org Q4_K_M GGUF (official ggml-org repo).
In a PC with enough normal memory it runs slowly: PC with Radeon RX 7900 XTX 24GB, about $2,422€2,354 (with a used graphics card).
Updated · Recursive Flint on every card
How much memory it needs
That is about 1.0 times what this card has free.
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.
What runs Recursive Flint instead
The cheapest machine on our list that holds the whole model in its graphics memory:
Mac mini M4 Pro 64GBabout $2,116€1,890
EU shops · Shown to visitors in Europe.US shops · Shown to visitors outside Europe.
We never pass off an estimate as a benchmark. Commissions never change which hardware we recommend. How we calculate
Price details
$2,116€1,890
How we priced this
Not checked against a shop listing (price unverified). Price from 16 Oct 2026.
Used-market euro amount from an earlier check of ours. Used prices cannot be checked on the Apple Store.
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.
See our picks for Recursive Flint in Find hardware. Add your budget to see cheaper machines.
For comparison, an RX 7900 XTX costs $1,404€1,254, used (3-month median). Card details
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.
Recursive Flint on other graphics cards
Runs well3
The whole model fits in the graphics memory.
Doesn't fit7
Not enough graphics memory: it needs about 24.5 GB.
- 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
More about the model itself, what it is good at and its licence: Recursive Flint.
The numbers behind this answer
A model comes in several sizes. Q4 is the standard one most people use; the bigger ones answer a little better but need more memory. Each row adds up the model file, the memory a conversation takes, and some working space, and compares the total with what is free on this card.
Swipe the table sideways to see every column.
| Quality | Conversation | Result | Model file | Conversation memory | Working space | Total needed | Free memory |
|---|---|---|---|---|---|---|---|
| UD-Q3_K_XL (3-bit, unsloth/flint-GGUF) | ~4 pages8,192 tokens | Runs | 18.5 GBmeasured file | 0.3 GB | 0.8 GB | 19.6 GB | 23.4 GB |
| Q4 · standard (smallest that keeps quality) | ~12 pages8,192 tokens | Doesn't fit | 23.4 GBmeasured file | 0.3 GB | 0.8 GB | 24.5 GB | 23.4 GB |
| Q5 · a bit sharper, a bit bigger | ~12 pages8,192 tokens | Doesn't fit | 28.3 GB | 0.3 GB | 0.8 GB | 29.3 GB | 23.4 GB |
| Q8 · near full quality, almost twice Q4 | ~12 pages8,192 tokens | Doesn't fit | 42.6 GB | 0.3 GB | 0.8 GB | 43.6 GB | 23.4 GB |
| FP16 · full quality, over three times Q4 | ~12 pages8,192 tokens | Doesn't fit | 79.6 GB | 0.3 GB | 0.8 GB | 80.7 GB | 23.4 GB |
| Q4 · standard, longer conversation | ~49 pages32,768 tokens | Doesn't fit | 23.4 GBmeasured file | 1.0 GB | 0.8 GB | 25.2 GB | 23.4 GB |
speed: not estimated for MoE yet. This model only uses part of itself for each word (a mixture of experts), and our speed estimate does not handle that yet.
Sources and method
Memory and speed on this page are our estimate, not a measured test. Checked . ggml-org Q4_K_M GGUF (official ggml-org repo).
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.
Measured Recursive Flint on an RX 7900 XTX yourself? Send us your llama-bench result.
Questions
- Can I run Recursive Flint on an RX 7900 XTX?
- Not at 4-bit Q4_K_M, which needs about 24.5 GB (24.46 GB estimate) while an RX 7900 XTX leaves about 23.4 GB usable out of 24 GB. It fits on a single an RX 7900 XTX at 3-bit UD-Q3_K_XL (unsloth/flint-GGUF, 18.49 GB measured weights, 19.56 GB total estimate at 8,192 context, leaving about 3.8 GB spare).
- How much memory does Recursive Flint need?
- About 24.5 GB at the standard quality (Q4) for a conversation of up to about 12 pages of text (8,192 tokens), by our estimate: 23.4 GB for the model file (measured), 0.3 GB to hold the conversation and 0.8 GB of working space.
- How fast is Recursive Flint on an RX 7900 XTX?
- 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.
Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate