MI

failspy Codestral 22B v0.1 abliterated v3

MistralGGUF by RichardErkhovUpdated 2024-09-17
Download on Hugging Face
Parameters22.2B
Context32K
Layers56
Architecturellama
Smallest quant8.3 GB
Quick answer

failspy Codestral 22B v0.1 abliterated v3 needs about 15.7 GB of memory at Q4_K_M (a 13.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 22 quants, from 8.3 GB (Q2_K) to 23.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

22B parameter LLM focused on coding

Failspy Codestral 22B v0.1 abliterated v3 is a 22.2B parameter model based on the Mistral family. It is trained for a 32768 token context and is tuned to reduce refusal behavior. The model is available in multiple GGUF quantizations.

Good at

  • coding tasks
  • large context handling
  • low refusal propensity

Limits

  • no vision support
  • no license specified
  • requires large VRAM for higher quants

Best for

  • code generation
  • debugging assistance
  • algorithmic explanations

Who it’s for. Developers and researchers needing a large language model specialized for code. The model is suitable for environments where a 32k token context is beneficial and where reduced refusal is desired.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K8.3 GB 10.7 GB
Too big Get file →
IQ3_XS9.2 GB 11.6 GB
Too big Get file →
Q3_K_S9.6 GB 12.0 GB
Too big Get file →
IQ3_S9.7 GB 12.1 GB
Too big Get file →
IQ3_M10.1 GB 12.4 GB
Too big Get file →
Q3_K10.8 GB 13.1 GB
Too big Get file →
Q3_K_M10.8 GB 13.1 GB
Too big Get file →
Q3_K_L11.7 GB 14.1 GB
Too big Get file →
IQ4_XS12.0 GB 14.4 GB
Too big Get file →
Q4_012.6 GB 14.9 GB
Too big Get file →
Q4_K_S12.7 GB 15.0 GB
Too big Get file →
IQ4_NL12.7 GB 15.1 GB
Too big Get file →
Q4_K13.3 GB 15.7 GB
Too big Get file →
Q4_K_M13.3 GB 15.7 GB
Too big Get file →
Q4_113.9 GB 16.3 GB
Too big Get file →
Q5_015.3 GB 17.7 GB
Too big Get file →
Q5_K_S15.3 GB 17.7 GB
Too big Get file →
Q5_K15.7 GB 18.1 GB
Too big Get file →
Q5_K_M15.7 GB 18.1 GB
Too big Get file →
Q5_116.7 GB 19.1 GB
Too big Get file →
Q6_K18.3 GB 20.6 GB
Too big Get file →
Q8_023.6 GB 26.0 GB
Too big Get file →

For 8‑GB VRAM use Q2_K (8.27 GB file, ~10.7 GB memory). For 12‑GB VRAM use Q3_K_S (9.64 GB file, ~12 GB memory). For 16‑GB VRAM use Q4_K (13.34 GB file, ~15.7 GB memory). Memory estimates are approximate.

What GPU do you need for failspy Codestral 22B v0.1 abliterated v3?

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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q3_K_S (9.6 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K (13.3 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (18.3 GB file, about 20.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (23.6 GB file, about 26.0 GB in use).

Which failspy Codestral 22B v0.1 abliterated v3 quant should you choose?

Q4_K_M is the usual starting point for failspy Codestral 22B v0.1 abliterated v3: it balances file size and quality well. Here it is a 13.3 GB file.

The Q8_0 file is 23.6 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 8.3 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
Parameters22.2B
Layers56
Trained context32,768 tokens
KV cache (fp16)224 KB per token

Source

Quantized byRichardErkhov
FamilyMistral
Downloads (HF)1,839
Last updated2024-09-17

Frequently asked questions about failspy Codestral 22B v0.1 abliterated v3

How much VRAM does failspy Codestral 22B v0.1 abliterated v3 need?

About 15.7 GB at Q4_K_M with an 8K context window. That is the 13.3 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 failspy Codestral 22B v0.1 abliterated v3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of failspy Codestral 22B v0.1 abliterated v3 GGUF?

It depends on the quant: Q2_K is 8.3 GB, IQ3_XS is 9.2 GB, Q3_K_S is 9.6 GB, IQ3_S is 9.7 GB, IQ3_M is 10.1 GB, Q3_K is 10.8 GB and 16 more.

What context length does failspy Codestral 22B v0.1 abliterated v3 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download failspy Codestral 22B v0.1 abliterated v3 GGUF?

The files are on Hugging Face in the RichardErkhov/failspy_-_Codestral-22B-v0.1-abliterated-v3-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, the Q2_K quantization requires about 10.7 GB of VRAM at 8k context, which fits within an 8 GB GPU with some overhead.

Does this model support image input?

No, the model has no vision capabilities.

Is the model licensed for commercial use?

The license is not specified in the provided information.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Mistral models

All Mistral →

Other medium models

All medium models →