LL

MSH Lite 7B v1 Bielik v2.3 Instruct Llama Prune

LlamaGGUF by mradermacherUpdated 2025-03-02
Download on Hugging Face
Parameters7.65B
Context32K
Layers50
Architecturellama
Smallest quant5.7 GB
Quick answer

MSH Lite 7B v1 Bielik v2.3 Instruct Llama Prune needs about 8.0 GB of memory at IQ3_XXS (a 5.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 5.7 GB (Q2_K) to 6.9 GB (Q4_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 6.7 GB.

MSH Lite 7B v1 Bielik v2.3 Instruct Llama Prune is a 7.65B-parameter Llama model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 4 quant files, from 5.7 GB (Q2_K) to 6.9 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.7 GB 7.8 GB
Tight Get file →
IQ3_XXS5.8 GB 8.0 GB
Too big Get file →
IQ3_M6.2 GB 8.4 GB
Too big Get file →
Q4_K_S6.9 GB 9.0 GB
Too big Get file →

What GPU do you need for MSH Lite 7B v1 Bielik v2.3 Instruct Llama Prune?

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: the best quant that fits is IQ3_XXS (5.8 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_S (6.9 GB file, about 9.0 GB in use).

Which MSH Lite 7B v1 Bielik v2.3 Instruct Llama Prune quant should you choose?

IQ3_XXS (5.8 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 Q2_K at 5.7 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

Architecturellama
Parameters7.65B
Layers50
Trained context32,768 tokens
KV cache (fp16)200 KB per token

Frequently asked questions about MSH Lite 7B v1 Bielik v2.3 Instruct Llama Prune

How much VRAM does MSH Lite 7B v1 Bielik v2.3 Instruct Llama Prune need?

About 8.0 GB at IQ3_XXS with an 8K context window. That is the 5.8 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 MSH Lite 7B v1 Bielik v2.3 Instruct Llama Prune on an 8 GB GPU?

Yes, with IQ3_XXS: the 5.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MSH Lite 7B v1 Bielik v2.3 Instruct Llama Prune GGUF?

It depends on the quant: Q2_K is 5.7 GB, IQ3_XXS is 5.8 GB, IQ3_M is 6.2 GB, Q4_K_S is 6.9 GB.

What context length does MSH Lite 7B v1 Bielik v2.3 Instruct Llama Prune support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.7 GB at 32K.

Where can I download MSH Lite 7B v1 Bielik v2.3 Instruct Llama Prune GGUF?

The files are on Hugging Face in the mradermacher/MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune-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 MSH Lite 7B v1 Bielik v2.3 Instruct Llama Prune 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 MSH-Lite-7B-v1-Bielik-v2.3-Instruct-Llama-Prune

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →