MI

Ft Mistral 7b Instruct v0.2 Sorry Bench 202406

MistralGGUF by RichardErkhovUpdated 2024-09-20
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant2.7 GB
Quick answer

Ft Mistral 7b Instruct v0.2 Sorry Bench 202406 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 22 quants, from 2.7 GB (Q2_K) to 7.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Ft Mistral 7b Instruct v0.2 – a fine‑tuned safety evaluator

Ft Mistral 7b Instruct v0.2 is a 7.24‑billion‑parameter Mistral model fine‑tuned on the SORRY‑Bench dataset. It is released under the MIT license and supports text generation with a 32768‑token context window.

Good at

  • Safety refusal evaluation
  • Human‑judgment benchmark
  • Text‑generation tasks

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • No other language support listed

Best for

  • Evaluating LLM safety responses
  • Benchmarking safety metrics
  • Generating safety‑aware text

Who it’s for. Developers and researchers who need a lightweight safety judge for LLMs. The model is suitable for local deployment on systems with limited GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 4.3 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_K3.5 GB 5.1 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 →
IQ4_NL4.2 GB 5.7 GB
Fits Get file →
Q4_K4.4 GB 5.9 GB
Fits Get file →
Q4_K_M4.4 GB 5.9 GB
Fits Get file →
Q4_14.6 GB 6.1 GB
Fits Get file →
Q5_05.0 GB 6.6 GB
Fits Get file →
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K5.1 GB 6.7 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q5_15.4 GB 7.0 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →

For 8‑GB VRAM use Q4_0 (file size 4.11 GB, estimated 5.7 GB memory). For 12‑GB VRAM use Q5_0 (5 GB, 6.6 GB memory). For 24‑GB VRAM use Q6_K (5.94 GB, 7.5 GB memory).

What GPU do you need for Ft Mistral 7b Instruct v0.2 Sorry Bench 202406?

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: the best quant that fits is Q4_K (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).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).

Which Ft Mistral 7b Instruct v0.2 Sorry Bench 202406 quant should you choose?

Q4_K_M is the usual starting point for Ft Mistral 7b Instruct v0.2 Sorry Bench 202406: it balances file size and quality well. Here it is a 4.4 GB file.

The Q8_0 file is 7.7 GB, about 1.8 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 Q2_K at 2.7 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
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byRichardErkhov
FamilyMistral
Licensemit
Downloads (HF)798
Last updated2024-09-20

Frequently asked questions about Ft Mistral 7b Instruct v0.2 Sorry Bench 202406

How much VRAM does Ft Mistral 7b Instruct v0.2 Sorry Bench 202406 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 Ft Mistral 7b Instruct v0.2 Sorry Bench 202406 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 Ft Mistral 7b Instruct v0.2 Sorry Bench 202406 GGUF?

It depends on the quant: Q2_K is 2.7 GB, IQ3_XS is 3.0 GB, Q3_K_S is 3.2 GB, IQ3_S is 3.2 GB, IQ3_M is 3.3 GB, Q3_K is 3.5 GB and 16 more.

What context length does Ft Mistral 7b Instruct v0.2 Sorry Bench 202406 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 Ft Mistral 7b Instruct v0.2 Sorry Bench 202406 GGUF?

The files are on Hugging Face in the RichardErkhov/sorry-bench_-_ft-mistral-7b-instruct-v0.2-sorry-bench-202406-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 Ft Mistral 7b Instruct v0.2 Sorry Bench 202406 use?

Hugging Face lists the license as mit. 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 this model on 8 GB VRAM?

Yes, the Q4_0 quantization requires about 5.7 GB of VRAM at 8‑k context.

Does the model support other languages?

No language support beyond English is listed in the metadata.

Is the model safe for public deployment?

It is licensed under MIT and designed for safety evaluation, but no explicit safety guarantees are provided.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Mistral models

All Mistral →

Other small models

All small models →