FL

Flint Preview

FlintGGUF by unslothUpdated 2026-10-21
Download on Hugging Face
Parameters39.8B
Context256K
Layers49
Architectureflint
Smallest quant11.4 GB
Quick answer

Flint Preview needs about 19.8 GB of memory at Q3_K_XL (a 18.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 11.4 GB (IQ1_M) to 79.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.3 GB.

Flint Preview – 40B mixture‑of‑experts model for coding tasks

Flint Preview is a 40‑billion‑parameter mixture‑of‑experts language model designed for coding agents. It supports text input and output, reasoning, and multi‑turn tool use. The model is available in multiple GGUF quantizations for local deployment.

Good at

  • Codebase investigation
  • Bug fixing
  • Feature implementation

Limits

  • Requires large VRAM for full precision
  • No vision support
  • License is Apache‑2.0

Best for

  • Developers testing code generation
  • Automated bug‑fix pipelines
  • Writing unit tests

Who it’s for. Engineers and researchers who need a local coding assistant. The model runs on NVIDIA or Apple Silicon GPUs using llama.cpp or SGLang.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M11.4 GB 12.7 GB
Too big Get file →
IQ2_XXS11.9 GB 13.2 GB
Too big Get file →
Q2_K_XL13.6 GB 14.9 GB
Too big Get file →
IQ3_XXS14.5 GB 15.9 GB
Too big Get file →
Q3_K_XL18.5 GB 19.8 GB
Too big Get file →
Q4_K_XL25.1 GB 26.4 GB
Too big Get file →
Q5_K_XL29.9 GB 31.2 GB
Too big Get file →
Q6_K_XL36.3 GB 37.6 GB
Too big Get file →
Q8_042.3 GB 43.6 GB
Too big Get file →
BF1679.6 GB (3 parts) 80.9 GB
Too big Get file →

For 8‑GB VRAM use IQ1_M (11.35 GB, ~12.7 GB memory at 8k context). For 12‑GB VRAM use IQ2_XXS (11.86 GB, ~13.2 GB). For 16‑GB VRAM use Q2_K_XL (13.56 GB, ~14.9 GB). Larger models require 24‑GB or more VRAM.

What GPU do you need for Flint Preview?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (14.5 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q3_K_XL (18.5 GB file, about 19.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_XL (29.9 GB file, about 31.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (42.3 GB file, about 43.6 GB in use).

Which Flint Preview quant should you choose?

Q3_K_XL (18.5 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_M at 11.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureflint
Parameters39.8B (approximate, mixture of experts)
Layers49
Trained context262,144 tokens
KV cache (fp16)98 KB per token

Source

Quantized byunsloth
FamilyFlint
Licenseapache-2.0
Downloads (HF)201,035
Last updated2026-10-21

Frequently asked questions about Flint Preview

How much VRAM does Flint Preview need?

About 19.8 GB at Q3_K_XL with an 8K context window. That is the 18.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Flint Preview on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Flint Preview GGUF?

It depends on the quant: IQ1_M is 11.4 GB, IQ2_XXS is 11.9 GB, Q2_K_XL is 13.6 GB, IQ3_XXS is 14.5 GB, Q3_K_XL is 18.5 GB, Q4_K_XL is 25.1 GB and 4 more.

What context length does Flint Preview support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.3 GB at 32K.

Where can I download Flint Preview GGUF?

The files are on Hugging Face in the unsloth/flint-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Flint Preview use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Flint Preview on 8 GB VRAM?

Use the IQ1_M quantization; it requires about 12.7 GB of VRAM at 8k context, so 8 GB is insufficient.

Does Flint support image input?

No, Flint only handles text input and output.

What license applies to Flint Preview?

Flint Preview is released under the Apache‑2.0 license.

Other GGUFs of flint

Similar models

Browse all →

More from unsloth

All by unsloth →

More Flint models

All Flint →

Other large models

All large models →