MI

TowerInstruct Mistral 7B v0.2

MistralGGUF by mradermacherUpdated 2024-09-04
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant1.6 GB
Quick answer

TowerInstruct Mistral 7B v0.2 needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 21 quants, from 1.6 GB (IQ1_S) to 5.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

TowerInstruct Mistral 7B v0.2 – a 7B parameter translation‑focused model

TowerInstruct Mistral 7B v0.2 is a 7.24 billion parameter model fine‑tuned on the TowerBlocks dataset. It supports translation, post‑editing, named‑entity recognition, grammatical error correction, paraphrase generation, and code instructions. The model is licensed under CC‑BY‑NC‑4.0.

Good at

  • Translation of sentences and paragraphs
  • Post‑editing and terminology‑aware translation
  • Named‑entity recognition and paraphrase generation

Limits

  • Not intended for general chatbot or code assistant use
  • Limited to the 10 supported languages
  • No vision support

Best for

  • Document‑level translation tasks
  • Post‑editing workflows
  • Multilingual NLP pipelines

Who it’s for. Developers and researchers needing a compact translation model for English, Portuguese, Spanish, French, German, Dutch, Italian, Korean, Chinese, and Russian. The model is suitable for integration into translation tools and NLP pipelines where a 7B parameter size is desired.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.6 GB 3.2 GB
Fits Get file →
IQ1_M1.8 GB 3.3 GB
Fits Get file →
IQ2_XXS2.0 GB 3.6 GB
Fits Get file →
IQ2_XS2.2 GB 3.8 GB
Fits Get file →
IQ2_S2.3 GB 3.9 GB
Fits Get file →
IQ2_M2.5 GB 4.1 GB
Fits Get file →
Q2_K2.7 GB 4.3 GB
Fits Get file →
IQ3_XXS2.8 GB 4.4 GB
Fits Get file →
IQ3_XS3.0 GB 4.6 GB
Fits Get file →
Q3_K_S3.2 GB 4.7 GB
Fits Get file →
IQ3_S3.2 GB 4.8 GB
Fits Get file →
IQ3_M3.3 GB 4.9 GB
Fits Get file →
Q3_K_M3.5 GB 5.1 GB
Fits Get file →
Q3_K_L3.8 GB 5.4 GB
Fits Get file →
IQ4_XS3.9 GB 5.5 GB
Fits Get file →
Q4_04.1 GB 5.7 GB
Fits Get file →
Q4_K_S4.1 GB 5.7 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →

For 8 GB VRAM use IQ1_S (1.61 GB, 3.2 GB memory at 8k context) or IQ1_M (1.75 GB, 3.3 GB). With 12 GB VRAM, IQ2_S (2.31 GB, 3.9 GB) or Q2_K (2.72 GB, 4.3 GB) are suitable. For 24 GB VRAM, Q5_K_M (5.13 GB, 6.7 GB) or Q6_K (5.94 GB, 7.5 GB) provide higher quality.

What GPU do you need for TowerInstruct Mistral 7B v0.2?

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 IQ2_S (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).

Which TowerInstruct Mistral 7B v0.2 quant should you choose?

Q4_K_M is the usual starting point for TowerInstruct Mistral 7B v0.2: it balances file size and quality well. Here it is a 4.4 GB file.

If memory is tight, the smallest file is IQ1_S at 1.6 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyMistral
Downloads (HF)3,008
Last updated2024-09-04

Frequently asked questions about TowerInstruct Mistral 7B v0.2

How much VRAM does TowerInstruct Mistral 7B v0.2 need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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 TowerInstruct Mistral 7B v0.2 on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TowerInstruct Mistral 7B v0.2 GGUF?

It depends on the quant: IQ1_S is 1.6 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.3 GB, IQ2_M is 2.5 GB and 15 more.

What context length does TowerInstruct Mistral 7B v0.2 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 TowerInstruct Mistral 7B v0.2 GGUF?

The files are on Hugging Face in the mradermacher/TowerInstruct-Mistral-7B-v0.2-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 TowerInstruct Mistral 7B v0.2 use?

Hugging Face lists the license as cc-by-nc-4.0. 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 TowerInstruct Mistral 7B v0.2 on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quants will fit within 8 GB VRAM with approximate memory usage of 3.2–3.3 GB at 8k context.

Is the model suitable for chat applications?

No, the model is not intended as a conversational chatbot or code assistant.

Which languages are supported?

English, Portuguese, Spanish, French, German, Dutch, Italian, Korean, Chinese, and Russian.

Other GGUFs of TowerInstruct-Mistral-7B-v0.2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mistral models

All Mistral →

Other small models

All small models →