MI

kolibri-vikhr-mistral-0427

MistralGGUF by VikhrmodelsUpdated 2024-05-25
Download on Hugging Face
Parameters7.6B
Context32K
Layers32
Architecturellama
Smallest quant4.6 GB
Quick answer

kolibri-vikhr-mistral-0427 needs about 6.2 GB of memory at Q4_K_M (a 4.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 4.6 GB (Q4_K_M) to 8.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Instruction following model optimized for Russian language

kolibri-vikhr-mistral-0427 is a 7.6 billion‑parameter Mistral model based on the llama architecture. It supports instruction following with the ChatML template and is tuned for Russian language tasks such as retrieval, classification, semantic analysis, and translation.

Good at

  • Russian instruction following
  • Semantic analysis
  • Translation (en‑ru)

Limits

  • No vision support
  • Requires 8 k context for estimates
  • License: apache‑2.0

Best for

  • Information retrieval in Russian
  • Russian text classification
  • Russian‑English translation

Who it’s for. Developers building Russian‑centric chat or retrieval systems. Researchers needing a lightweight Mistral variant for Russian language tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.6 GB 6.2 GB
Fits Get file →
Q5_K_M5.4 GB 7.0 GB
Fits Get file →
Q8_08.1 GB 9.7 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (4.64 GB, ~6.2 GB memory). For 12 GB VRAM Q5_K_M (5.42 GB, ~7 GB memory). Q8_0 requires ~9.7 GB memory and 8.11 GB file size.

What GPU do you need for kolibri-vikhr-mistral-0427?

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 Q5_K_M (5.4 GB file, about 7.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.7 GB in use).

Which kolibri-vikhr-mistral-0427 quant should you choose?

Q4_K_M is the usual starting point for kolibri-vikhr-mistral-0427: it balances file size and quality well. Here it is a 4.6 GB file.

The Q8_0 file is 8.1 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.6B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byVikhrmodels
FamilyMistral
Licenseapache-2.0
Downloads (HF)4,383
Last updated2024-05-25

Frequently asked questions about kolibri-vikhr-mistral-0427

How much VRAM does kolibri-vikhr-mistral-0427 need?

About 6.2 GB at Q4_K_M with an 8K context window. That is the 4.6 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 kolibri-vikhr-mistral-0427 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.4 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of kolibri-vikhr-mistral-0427 GGUF?

It depends on the quant: Q4_K_M is 4.6 GB, Q5_K_M is 5.4 GB, Q8_0 is 8.1 GB.

What context length does kolibri-vikhr-mistral-0427 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download kolibri-vikhr-mistral-0427 GGUF?

The files are on Hugging Face in the Vikhrmodels/kolibri-vikhr-mistral-0427 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does kolibri-vikhr-mistral-0427 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 kolibri-vikhr-mistral-0427 on 8 GB VRAM?

Yes, the Q4_K_M quantization uses about 6.2 GB of VRAM at 8 k context, fitting within an 8 GB GPU.

Does this model support vision tasks?

No, it is a text‑only model with no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from Vikhrmodels

All by Vikhrmodels →

More Mistral models

All Mistral →

Other small models

All small models →