Can I run Flint locally?
Flint by RecursiveSI has 40B parameters (1.3B active per token, 256 experts, 6 used per token). At 4-bit with an 8K context it needs about 24.5 GB of GPU memory. It fits on 36 of 65 GPUs and Macs we track. See all models that fit in 32 GB of VRAM.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from bartowski/RecursiveSI_flint-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx | 8K ctx | 32K ctx | 128K ctx |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | rough | 15.2 GB | 15.4 GB | 16.0 GB | 18.6 GB |
| 3-bit (Q3_K_M) • | usable | 19.0 GB | 19.1 GB | 19.8 GB | 22.4 GB |
| 4-bit (Q4_K_M) • | good, most popular | 24.4 GB | 24.5 GB | 25.2 GB | 27.8 GB |
| 5-bit (Q5_K_M) • | very good | 29.5 GB | 29.6 GB | 30.3 GB | 32.9 GB |
| 6-bit (Q6_K) • | near lossless | 33.6 GB | 33.7 GB | 34.4 GB | 37.0 GB |
| 8-bit (Q8_0) • | effectively lossless | 40.3 GB | 40.4 GB | 41.0 GB | 43.7 GB |
| 16-bit (F16/BF16) • | original weights | 75.0 GB | 75.1 GB | 75.8 GB | 78.4 GB |
Which GPUs and Macs run Flint?
Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).
Prefer an API?
Recursive: Flint (free) is on OpenRouter at free per 1M input tokens and free per 1M output tokens. Price details and history →
Questions
How much VRAM does Flint need?
About 24.5 GB at 4-bit (Q4_K_M) with an 8K context: 23.6 GB of weights (real GGUF file size), 0.3 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 40.4 GB.
What is the smallest GPU that runs Flint?
At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 5090 (32 GB).
Can I run Flint on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M4 Pro 48GB or larger, using the default macOS GPU memory limit.
Similar models
Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.
Falcon 40B
42B · 25.2 GB at 4-bitMaxwell V1 Flash
37B · 22.1 GB at 4-bitHermes 4.3 36B
36B · 23.0 GB at 4-bitSeed OSS 36B Instruct
36B · 23.0 GB at 4-bitQwen3.6 35B A3B
36B · 21.8 GB at 4-bitOrnith 1.5 35B A3B
36B · 21.4 GB at 4-bitEmbed this
Free badge and "Will it run on my GPU?" widget for model cards, READMEs and blogs. No cookies, no tracking. All options.
Copy a snippet
Markdown badge
[](https://runsonmy.com/model/flint/) Widget (script)
<div class="runsonmy-widget" data-model="flint"><a href="https://runsonmy.com/model/flint/">Will Flint run on my GPU? Check on RunsOnMy</a></div>
<script async src="https://runsonmy.com/embed.js"></script> Widget (iframe)
<iframe src="https://runsonmy.com/embed/m/flint/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will Flint run on my GPU? (RunsOnMy)"></iframe> Model facts
| Hugging Face repo | RecursiveSI/flint |
| Parameters | 39,785,287,456 (40B) · ~1.3B active (computed from config) |
| Layers / hidden size | 49 / 2048 |
| Attention | GQA + sliding window; 32 heads, 4 KV heads, head dim 128; sliding window 513 |
| KV cache per token (FP16) | 98.0 KiB (sliding layers capped at the window) |
| Max context | 262,144 tokens |
| License | apache-2.0 |
| Released on HF | Oct 21, 2026 |
| Downloads (30d) / likes | 59,329 / 1,417 |
Sources: Hugging Face model API · config.json (RecursiveSI/flint) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.