Falcon H1 Tiny Coder 90M needs about 0.7 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 27 quants, from 0.0 GB (IQ2_M) to 0.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.
Falcon H1 Tiny Coder 90M – lightweight code generation model
Falcon H1 Tiny Coder 90M is a 90M parameter causal decoder-only model designed for Python code generation and fill‑in‑the‑middle tasks. It is available in GGUF format and supports inference via llama.cpp, vLLM, sglang, ollama, and mlx.
Good at
- Python code generation
- Python fill‑in‑the‑middle
- Lightweight inference
Limits
- No vision support
- License is Falcon‑LLM
- Limited to 262144 context tokens
Best for
- Small‑scale coding assistants
- Embedded code generation
- Rapid prototyping
Who it’s for. Developers needing a small, fast code generation model for Python. Researchers testing lightweight Falcon variants. Hobbyists running models on modest hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 0.0 GB | 0.6 GB | Fits | Get file → | |
| IQ3_XXS | 0.0 GB | 0.6 GB | Fits | Get file → | |
| TQ1_0 | 0.0 GB | 0.6 GB | Fits | Get file → | |
| TQ2_0 | 0.0 GB | 0.6 GB | Fits | Get file → | |
| Q2_K | 0.0 GB | 0.6 GB | Fits | Get file → | |
| IQ3_XS | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q3_K_S | 0.1 GB | 0.7 GB | Fits | Get file → | |
| IQ3_S | 0.1 GB | 0.7 GB | Fits | Get file → | |
| IQ3_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q3_K | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q3_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q3_K_L | 0.1 GB | 0.7 GB | Fits | Get file → | |
| IQ4_XS | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_K_S | 0.1 GB | 0.7 GB | Fits | Get file → | |
| IQ4_NL | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_K | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_1 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_S | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_K | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_1 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q6_K | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| BF16 | 0.2 GB | 0.8 GB | Fits | Get file → |
For 8 GB VRAM, use IQ2_M or IQ3_XXS (file size 0.02 GB, memory 0.6 GB). For 4 GB VRAM, IQ3_XS or Q3_K_S (0.05 GB, 0.7 GB). For 2 GB VRAM, IQ3_S or Q3_K (0.05 GB, 0.7 GB).
What GPU do you need for Falcon H1 Tiny Coder 90M?
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: the best quant that fits is BF16 (0.2 GB file, about 0.8 GB in use).
Which Falcon H1 Tiny Coder 90M quant should you choose?
Q4_K_M is the usual starting point for Falcon H1 Tiny Coder 90M: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.1 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ2_M at 0.0 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
Source
Frequently asked questions about Falcon H1 Tiny Coder 90M
How much VRAM does Falcon H1 Tiny Coder 90M need?
About 0.7 GB at Q4_K_M with an 8K context window. That is the 0.1 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 Falcon H1 Tiny Coder 90M on an 8 GB GPU?
Yes, with BF16: the 0.2 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Falcon H1 Tiny Coder 90M GGUF?
It depends on the quant: IQ2_M is 0.0 GB, IQ3_XXS is 0.0 GB, TQ1_0 is 0.0 GB, TQ2_0 is 0.0 GB, Q2_K is 0.0 GB, IQ3_XS is 0.1 GB and 21 more.
What context length does Falcon H1 Tiny Coder 90M support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.
Where can I download Falcon H1 Tiny Coder 90M GGUF?
The files are on Hugging Face in the tiiuae/Falcon-H1-Tiny-Coder-90M-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 Falcon H1 Tiny Coder 90M use?
Hugging Face lists the license as other. 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 Falcon H1 Tiny Coder 90M on 4 GB VRAM?
Yes, using IQ3_XS or Q3_K_S quantizations which require about 0.7 GB memory at 8k context.
Does this model support image inputs?
No, it is a text‑only causal decoder model.
What license applies to this model?
The model is released under the Falcon‑LLM License.