MI

mirrorqwen2.5-0.5b-SimPO

MirrorqwenGGUF by mradermacherUpdated 2024-11-10
Download on Hugging Face
Parameters494M
Context32K
Layers24
Architectureqwen2
Smallest quant0.3 GB
Quick answer

mirrorqwen2.5-0.5b-SimPO needs about 1.0 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 13 quants, from 0.3 GB (Q3_K_S) to 1.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

MirrorQwen2.5‑0.5b‑SimPO – a fine‑tuned Qwen2 model

MirrorQwen2.5‑0.5b‑SimPO is a 0.494 billion‑parameter model fine‑tuned with Contrastive Preference Optimization. It supports a 32768‑token context window and is available in multiple GGUF quantizations.

Good at

  • Fine‑tuned conversational tasks
  • Contrastive preference‑optimized responses
  • Large context handling

Limits

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

Best for

  • Chatbot prototypes
  • Context‑heavy dialogue systems
  • Rapid prototyping with limited GPU

Who it’s for. Developers building lightweight LLM applications who need a 0.5 billion‑parameter model with a 32k context window. The model is suitable for environments with modest VRAM and for users who prefer GGUF quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S0.3 GB 0.9 GB
Fits Get file →
Q2_K0.3 GB 0.9 GB
Fits Get file →
IQ4_XS0.4 GB 1.0 GB
Fits Get file →
Q4_00.4 GB 1.0 GB
Fits Get file →
Q3_K_M0.4 GB 1.0 GB
Fits Get file →
Q3_K_L0.4 GB 1.0 GB
Fits Get file →
Q4_K_S0.4 GB 1.0 GB
Fits Get file →
Q4_K_M0.4 GB 1.0 GB
Fits Get file →
Q5_K_S0.4 GB 1.0 GB
Fits Get file →
Q5_K_M0.4 GB 1.0 GB
Fits Get file →
Q6_K0.5 GB 1.1 GB
Fits Get file →
Q8_00.5 GB 1.1 GB
Fits Get file →
F161.0 GB 1.6 GB
Fits Get file →

For 8 GB VRAM, use Q3_K_S or Q2_K (0.34 GB file, ~0.9 GB memory). For 12 GB VRAM, Q4_0 or Q3_K_M (0.35–0.36 GB file, ~1 GB memory) are suitable. For 16 GB VRAM, Q6_K or Q8_0 (0.51–0.53 GB file, ~1.1 GB memory) provide higher precision.

What GPU do you need for mirrorqwen2.5-0.5b-SimPO?

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 F16 (1.0 GB file, about 1.6 GB in use).

Which mirrorqwen2.5-0.5b-SimPO quant should you choose?

Q4_K_M is the usual starting point for mirrorqwen2.5-0.5b-SimPO: it balances file size and quality well. Here it is a 0.4 GB file.

The Q8_0 file is 0.5 GB, about 1.3 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 Q3_K_S at 0.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters494M
Layers24
Trained context32,768 tokens
KV cache (fp16)12 KB per token

Source

Quantized bymradermacher
Downloads (HF)629
Last updated2024-11-10

Frequently asked questions about mirrorqwen2.5-0.5b-SimPO

How much VRAM does mirrorqwen2.5-0.5b-SimPO need?

About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.4 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 mirrorqwen2.5-0.5b-SimPO on an 8 GB GPU?

Yes, with F16: the 1.0 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mirrorqwen2.5-0.5b-SimPO GGUF?

It depends on the quant: Q3_K_S is 0.3 GB, Q2_K is 0.3 GB, IQ4_XS is 0.4 GB, Q4_0 is 0.4 GB, Q3_K_M is 0.4 GB, Q3_K_L is 0.4 GB and 7 more.

What context length does mirrorqwen2.5-0.5b-SimPO support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.

Where can I download mirrorqwen2.5-0.5b-SimPO GGUF?

The files are on Hugging Face in the mradermacher/mirrorqwen2.5-0.5b-SimPO-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 MirrorQwen2.5‑0.5b‑SimPO on 8 GB VRAM?

Yes, using Q3_K_S or Q2_K quantizations, which require about 0.9 GB of VRAM at 8k context.

What is the maximum context length of this model?

The model supports up to 32768 tokens of context.

Does this model support vision tasks?

No, the model does not have vision capabilities.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mirrorqwen models

All Mirrorqwen →

Other tiny models

All tiny models →