CO

Q2.5 ColdBrew R1 Atrax i1

ColdbrewGGUF by mradermacherUpdated 2025-02-11
Download on Hugging Face
Parameters9.24B
Context128K
Layers35
Architectureqwen2
Smallest quant2.2 GB
Quick answer

Q2.5 ColdBrew R1 Atrax i1 needs about 6.7 GB of memory at Q4_K_M (a 5.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 2.2 GB (IQ1_S) to 7.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.

Q2.5 ColdBrew R1 Atrax i1 – 9.24B Qwen2 language model

Q2.5 ColdBrew R1 Atrax i1 is a 9.24B parameter Qwen2 model merged from multiple sources. It is quantized in several IQ and static formats and supports up to 131072 context tokens. The model focuses on reasoning tasks.

Good at

  • Reasoning
  • Large context handling
  • Low‑memory inference

Limits

  • No vision support
  • License not specified
  • No mixture of experts

Best for

  • Chatbots needing deep reasoning
  • Long‑form content generation
  • Research prototyping

Who it’s for. Developers and researchers who need a reasonably sized Qwen2 model with extensive context and low‑memory options. Suitable for environments with limited GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.2 GB 3.3 GB
Fits Get file →
IQ1_M2.4 GB 3.5 GB
Fits Get file →
IQ2_XXS2.7 GB 3.8 GB
Fits Get file →
IQ2_XS2.9 GB 4.0 GB
Fits Get file →
IQ2_S3.1 GB 4.2 GB
Fits Get file →
IQ2_M3.3 GB 4.4 GB
Fits Get file →
Q2_K_S3.4 GB 4.5 GB
Fits Get file →
Q2_K3.6 GB 4.7 GB
Fits Get file →
IQ3_XXS3.7 GB 4.8 GB
Fits Get file →
IQ3_XS4.0 GB 5.1 GB
Fits Get file →
Q3_K_S4.2 GB 5.3 GB
Fits Get file →
IQ3_S4.2 GB 5.3 GB
Fits Get file →
IQ3_M4.3 GB 5.4 GB
Fits Get file →
Q3_K_M4.6 GB 5.7 GB
Fits Get file →
Q3_K_L4.9 GB 6.0 GB
Fits Get file →
IQ4_XS5.1 GB 6.2 GB
Fits Get file →
IQ4_NL5.4 GB 6.4 GB
Fits Get file →
Q4_05.4 GB 6.5 GB
Fits Get file →
Q4_K_S5.4 GB 6.5 GB
Fits Get file →
Q4_K_M5.7 GB 6.7 GB
Fits Get file →
Q4_15.9 GB 7.0 GB
Fits Get file →
Q5_K_S6.4 GB 7.5 GB
Tight Get file →
Q5_K_M6.6 GB 7.7 GB
Tight Get file →
Q6_K7.6 GB 8.7 GB
Too big Get file →

For 8 GB VRAM, use Q5_K_M (file size 6.59 GB, estimated 7.7 GB memory). For 4 GB VRAM, use IQ2_XS (file size 2.95 GB, estimated 4 GB memory). Larger quants such as Q6_K exceed typical VRAM limits.

What GPU do you need for Q2.5 ColdBrew R1 Atrax i1?

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_XS (2.9 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_L (4.9 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.6 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (7.6 GB file, about 8.7 GB in use).

Which Q2.5 ColdBrew R1 Atrax i1 quant should you choose?

Q4_K_M is the usual starting point for Q2.5 ColdBrew R1 Atrax i1: it balances file size and quality well. Here it is a 5.7 GB file.

If memory is tight, the smallest file is IQ1_S at 2.2 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

Architectureqwen2
Parameters9.24B
Layers35
Trained context131,072 tokens
KV cache (fp16)70 KB per token

Source

Quantized bymradermacher
FamilyColdbrew
Downloads (HF)421
Last updated2025-02-11

Frequently asked questions about Q2.5 ColdBrew R1 Atrax i1

How much VRAM does Q2.5 ColdBrew R1 Atrax i1 need?

About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.7 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 Q2.5 ColdBrew R1 Atrax i1 on an 8 GB GPU?

Yes, with Q5_K_M: the 6.6 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Q2.5 ColdBrew R1 Atrax i1 GGUF?

It depends on the quant: IQ1_S is 2.2 GB, IQ1_M is 2.4 GB, IQ2_XXS is 2.7 GB, IQ2_XS is 2.9 GB, IQ2_S is 3.1 GB, IQ2_M is 3.3 GB and 18 more.

What context length does Q2.5 ColdBrew R1 Atrax i1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.

Where can I download Q2.5 ColdBrew R1 Atrax i1 GGUF?

The files are on Hugging Face in the mradermacher/Q2.5-ColdBrew-R1-Atrax-i1-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 Q5_K_M quant uses about 7.7 GB memory at 8k context, fitting within 8 GB VRAM.

Does this model support vision?

No, the model has no vision capabilities.

What is the maximum context length?

The model supports up to 131072 tokens of context.

Other GGUFs of Q2.5-ColdBrew-R1-Atrax

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Coldbrew models

All Coldbrew →

Other small models

All small models →