BI

BitCPM4 1B i1

BitcpmGGUF by mradermacherUpdated 2025-12-04
Download on Hugging Face
Parameters1.36B
Context32K
Layers52
Architectureminicpm
Smallest quant0.0 GB
Quick answer

BitCPM4 1B i1 needs about 2.2 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 1.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.

BitCPM4 1B i1 is a 1.36B-parameter Bitcpm model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 25 quant files, from 0.0 GB to 1.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.4 GB
Fits Get file →
IQ1_S0.3 GB 1.7 GB
Fits Get file →
IQ1_M0.4 GB 1.7 GB
Fits Get file →
IQ2_XXS0.4 GB 1.8 GB
Fits Get file →
IQ2_XS0.4 GB 1.8 GB
Fits Get file →
IQ2_S0.5 GB 1.8 GB
Fits Get file →
IQ2_M0.5 GB 1.9 GB
Fits Get file →
Q2_K_S0.5 GB 1.9 GB
Fits Get file →
Q2_K0.6 GB 1.9 GB
Fits Get file →
IQ3_XXS0.6 GB 1.9 GB
Fits Get file →
IQ3_XS0.6 GB 2.0 GB
Fits Get file →
IQ3_S0.6 GB 2.0 GB
Fits Get file →
Q3_K_S0.6 GB 2.0 GB
Fits Get file →
IQ3_M0.7 GB 2.0 GB
Fits Get file →
Q3_K_M0.7 GB 2.1 GB
Fits Get file →
Q3_K_L0.8 GB 2.1 GB
Fits Get file →
IQ4_XS0.8 GB 2.1 GB
Fits Get file →
IQ4_NL0.8 GB 2.2 GB
Fits Get file →
Q4_00.8 GB 2.2 GB
Fits Get file →
Q4_K_S0.8 GB 2.2 GB
Fits Get file →
Q4_K_M0.8 GB 2.2 GB
Fits Get file →
Q4_10.9 GB 2.2 GB
Fits Get file →
Q5_K_S1.0 GB 2.3 GB
Fits Get file →
Q5_K_M1.0 GB 2.3 GB
Fits Get file →
Q6_K1.1 GB 2.5 GB
Fits Get file →

What GPU do you need for BitCPM4 1B i1?

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 Q6_K (1.1 GB file, about 2.5 GB in use).

Which BitCPM4 1B i1 quant should you choose?

Q4_K_M is the usual starting point for BitCPM4 1B i1: it balances file size and quality well. Here it is a 0.8 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureminicpm
Parameters1.36B
Layers52
Trained context32,768 tokens
KV cache (fp16)104 KB per token

Source

Quantized bymradermacher
FamilyBitcpm
Licenseapache-2.0
Downloads (HF)202
Last updated2025-12-04

Frequently asked questions about BitCPM4 1B i1

How much VRAM does BitCPM4 1B i1 need?

About 2.2 GB at Q4_K_M with an 8K context window. That is the 0.8 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 BitCPM4 1B i1 on an 8 GB GPU?

Yes, with Q6_K: the 1.1 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of BitCPM4 1B i1 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.3 GB, IQ1_M is 0.4 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.5 GB and 19 more.

What context length does BitCPM4 1B i1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.5 GB at 32K.

Where can I download BitCPM4 1B i1 GGUF?

The files are on Hugging Face in the mradermacher/BitCPM4-1B-i1-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 BitCPM4 1B i1 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.

Other GGUFs of BitCPM4-1B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Bitcpm models

All Bitcpm →

Other tiny models

All tiny models →