QW

Qwen1.5 22B Chat Merge

QwenGGUF by mradermacherUpdated 2024-11-18
Download on Hugging Face
Parameters22B
Context32K
Layers65
Architectureqwen2
Smallest quant9.0 GB
Quick answer

Qwen1.5 22B Chat Merge needs about 25.7 GB of memory at Q4_K_M (a 14.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 11 quants, from 9.0 GB (Q2_K) to 23.4 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 43.6 GB.

Qwen1.5 22B Chat Merge – a 22B merged chat model

Qwen1.5 22B Chat Merge is a 22B parameter model created by interleaving layers of Qwen1.5‑14B‑Chat. It is available in multiple GGUF quantizations and supports a 32768 token context window.

Good at

  • Large context handling
  • Chat‑style interactions
  • Reasoning and coherence

Limits

  • No vision support
  • License is other
  • No intermediate‑size variants

Best for

  • Chatbots requiring long context
  • Research prototyping
  • Content generation with extended dialogue

Who it’s for. Users with GPUs that can handle 22B models and developers looking for a middle‑sized Qwen variant. It is suitable for those who need more capacity than 14B but cannot run 72B models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K9.0 GB 20.4 GB
Too big Get file →
Q3_K_S10.4 GB 21.8 GB
Too big Get file →
Q3_K_M11.4 GB 22.8 GB
Too big Get file →
Q3_K_L12.1 GB 23.5 GB
Too big Get file →
IQ4_XS12.2 GB 23.6 GB
Too big Get file →
Q4_K_S13.2 GB 24.6 GB
Too big Get file →
Q4_K_M14.3 GB 25.7 GB
Too big Get file →
Q5_K_S15.6 GB 27.0 GB
Too big Get file →
Q5_K_M16.4 GB 27.8 GB
Too big Get file →
Q6_K19.2 GB 30.6 GB
Too big Get file →
Q8_023.4 GB 34.8 GB
Too big Get file →

For 8 GB VRAM use Q2_K (9.04 GB file, ~20.4 GB memory). For 12 GB VRAM use Q3_K_S (10.4 GB file, ~21.8 GB memory). For 16 GB VRAM use Q4_K_M (14.28 GB file, ~25.7 GB memory).

What GPU do you need for Qwen1.5 22B Chat Merge?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is IQ4_XS (12.2 GB file, about 23.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (19.2 GB file, about 30.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (23.4 GB file, about 34.8 GB in use).

Which Qwen1.5 22B Chat Merge quant should you choose?

Q4_K_M is the usual starting point for Qwen1.5 22B Chat Merge: it balances file size and quality well. Here it is a 14.3 GB file.

The Q8_0 file is 23.4 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 Q2_K at 9.0 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
Parameters22B
Layers65
Trained context32,768 tokens
KV cache (fp16)1300 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseother
Downloads (HF)741
Last updated2024-11-18

Frequently asked questions about Qwen1.5 22B Chat Merge

How much VRAM does Qwen1.5 22B Chat Merge need?

About 25.7 GB at Q4_K_M with an 8K context window. That is the 14.3 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 Qwen1.5 22B Chat Merge on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen1.5 22B Chat Merge GGUF?

It depends on the quant: Q2_K is 9.0 GB, Q3_K_S is 10.4 GB, Q3_K_M is 11.4 GB, Q3_K_L is 12.1 GB, IQ4_XS is 12.2 GB, Q4_K_S is 13.2 GB and 5 more.

What context length does Qwen1.5 22B Chat Merge support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 10.9 GB at 8K and 43.6 GB at 32K.

Where can I download Qwen1.5 22B Chat Merge GGUF?

The files are on Hugging Face in the mradermacher/Qwen1.5-22B-Chat-Merge-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 Qwen1.5 22B Chat Merge 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 Qwen1.5 22B Chat Merge on 8 GB VRAM?

The Q2_K quant requires about 20.4 GB memory at 8 k context, so 8 GB VRAM is insufficient.

What is the maximum context length?

The model supports 32768 tokens.

Is there a vision capability?

No, the model does not support vision.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →