BL

blossom-v5-32b

BlossomGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters32.5B
Context32K
Layers64
Architectureqwen2
Smallest quant7.2 GB
Quick answer

blossom-v5-32b needs about 22.3 GB of memory at Q4_K_M (a 19.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 7.2 GB (IQ1_S) to 26.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

32.5B‑parameter Qwen2 conversational model

blossom‑v5‑32b is a 32.5B‑parameter conversational LLM based on Qwen2. It supports 32,768‑token context and is released under Apache‑2.0. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • General conversation
  • Multi‑turn dialogue

Limits

  • No vision support
  • Requires high VRAM for larger quants
  • No explicit language list

Best for

  • Chatbots with long context
  • Research prototyping
  • Content generation

Who it’s for. Developers and researchers needing a large conversational model with extensive context. The model is open‑source and can be run locally with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.2 GB 9.9 GB
Too big Get file →
IQ1_M7.9 GB 10.5 GB
Too big Get file →
IQ2_XXS9.0 GB 11.6 GB
Too big Get file →
IQ2_XS9.9 GB 12.5 GB
Too big Get file →
IQ2_S10.3 GB 13.0 GB
Too big Get file →
IQ2_M11.2 GB 13.8 GB
Too big Get file →
Q2_K12.2 GB 14.9 GB
Too big Get file →
IQ3_XXS12.7 GB 15.4 GB
Too big Get file →
IQ3_XS13.6 GB 16.3 GB
Too big Get file →
Q3_K_S14.3 GB 16.9 GB
Too big Get file →
IQ3_S14.3 GB 17.0 GB
Too big Get file →
IQ3_M14.7 GB 17.3 GB
Too big Get file →
Q3_K_M15.8 GB 18.5 GB
Too big Get file →
Q3_K_L17.1 GB 19.8 GB
Too big Get file →
IQ4_XS17.6 GB 20.2 GB
Too big Get file →
Q4_018.6 GB 21.2 GB
Too big Get file →
Q4_K_S18.6 GB 21.3 GB
Too big Get file →
Q4_K_M19.7 GB 22.3 GB
Too big Get file →
Q5_K_S22.5 GB 25.1 GB
Too big Get file →
Q5_K_M23.1 GB 25.7 GB
Too big Get file →
Q6_K26.7 GB 29.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7.22 GB file, 9.9 GB memory). For 12 GB VRAM, IQ2_M (11.18 GB file, 13.8 GB memory). For 16 GB VRAM, Q3_K_M (15.82 GB file, 18.5 GB memory). Estimates are approximate.

What GPU do you need for blossom-v5-32b?

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 IQ2_XXS (9.0 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (12.7 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (19.7 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.7 GB file, about 29.3 GB in use).

Which blossom-v5-32b quant should you choose?

Q4_K_M is the usual starting point for blossom-v5-32b: it balances file size and quality well. Here it is a 19.7 GB file.

If memory is tight, the smallest file is IQ1_S at 7.2 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
Parameters32.5B
Layers64
Trained context32,768 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyBlossom
Licenseapache-2.0
Downloads (HF)796
Last updated2024-08-02

Frequently asked questions about blossom-v5-32b

How much VRAM does blossom-v5-32b need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 19.7 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 blossom-v5-32b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of blossom-v5-32b GGUF?

It depends on the quant: IQ1_S is 7.2 GB, IQ1_M is 7.9 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 9.9 GB, IQ2_S is 10.3 GB, IQ2_M is 11.2 GB and 15 more.

What context length does blossom-v5-32b support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download blossom-v5-32b GGUF?

The files are on Hugging Face in the mradermacher/blossom-v5-32b-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 blossom-v5-32b use?

Hugging Face lists the license as apache-2.0. 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 blossom‑v5‑32b on 8 GB VRAM?

Use the IQ1_S quant, which requires about 9.9 GB memory at 8 k context.

Is blossom‑v5‑32b licensed for commercial use?

It is released under Apache‑2.0, which permits commercial use with attribution.

Does blossom‑v5‑32b support image inputs?

No, the model has no vision capability.

Other GGUFs of blossom-v5-32b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Blossom models

All Blossom →

Other medium models

All medium models →