MI

Riva Translate 4B Instruct v2 imatrix

MistralGGUF by liodon-aiUpdated 2026-07-29
Download on Hugging Face
Parameters4.2B
Context8K
Layers34
Architecturellama
Smallest quant1.8 GB
Quick answer

Riva Translate 4B Instruct v2 imatrix needs about 4.4 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 1.8 GB (IQ2_M) to 4.4 GB (Q8_0).

Riva Translate 4B Instruct v2 imatrix – 4.2B parameter LLM for instruction following

Riva Translate 4B Instruct v2 imatrix is a 4.2B parameter model based on Mistral-NeMo-12B-Base. It is quantized with iMatrix for improved instruction following. The model supports a 8192 token context window.

Good at

  • Instruction following
  • Translation tasks
  • Multilingual text generation

Limits

  • No vision support
  • License is other
  • No explicit multilingual benchmark data

Best for

  • Chatbot instruction handling
  • Translation services
  • Code documentation generation

Who it’s for. Developers needing a lightweight instruction-following model for translation or chat applications. The model is suitable for users who can run GGUF files with llama.cpp or similar engines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M1.8 GB 3.4 GB
Fits Get file →
IQ3_M2.2 GB 3.8 GB
Fits Get file →
IQ4_XS2.4 GB 4.0 GB
Fits Get file →
Q4_K_M2.8 GB 4.4 GB
Fits Get file →
Q5_K_M3.1 GB 4.8 GB
Fits Get file →
Q6_K3.7 GB 5.3 GB
Fits Get file →
Q8_04.4 GB 6.1 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.76 GB, estimated 4.4 GB memory). For 12 GB VRAM, Q5_K_M (3.14 GB, 4.8 GB memory) or Q6_K (3.66 GB, 5.3 GB memory) are suitable. For 16 GB VRAM, Q8_0 (4.45 GB, 6.1 GB memory) offers the highest quality.

What GPU do you need for Riva Translate 4B Instruct v2 imatrix?

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 IQ4_XS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.7 GB file, about 5.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.4 GB file, about 6.1 GB in use).

Which Riva Translate 4B Instruct v2 imatrix quant should you choose?

Q4_K_M is the usual starting point for Riva Translate 4B Instruct v2 imatrix: it balances file size and quality well. Here it is a 2.8 GB file.

The Q8_0 file is 4.4 GB, about 1.6 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 1.8 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
Parameters4.2B
Layers34
Trained context8,192 tokens
KV cache (fp16)136 KB per token

Source

Quantized byliodon-ai
FamilyMistral
Licenseother
Downloads (HF)786
Last updated2026-07-29

Frequently asked questions about Riva Translate 4B Instruct v2 imatrix

How much VRAM does Riva Translate 4B Instruct v2 imatrix need?

About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.8 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 Riva Translate 4B Instruct v2 imatrix on an 8 GB GPU?

Yes, with Q8_0: the 4.4 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Riva Translate 4B Instruct v2 imatrix GGUF?

It depends on the quant: IQ2_M is 1.8 GB, IQ3_M is 2.2 GB, IQ4_XS is 2.4 GB, Q4_K_M is 2.8 GB, Q5_K_M is 3.1 GB, Q6_K is 3.7 GB and 1 more.

What context length does Riva Translate 4B Instruct v2 imatrix support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download Riva Translate 4B Instruct v2 imatrix GGUF?

The files are on Hugging Face in the liodon-ai/Riva-Translate-4B-Instruct-v2-imatrix-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 Riva Translate 4B Instruct v2 imatrix 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 Riva Translate 4B Instruct v2 imatrix on 8 GB VRAM?

Yes, using Q4_K_M quantization which requires approximately 4.4 GB VRAM at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

What is the context window size?

The model supports up to 8192 tokens.

Similar models

Browse all →

More from liodon-ai

All by liodon-ai →

More Mistral models

All Mistral →

Other small models

All small models →