QW

Qwen2.5 Math 1.5B Instruct

QwenGGUF by legraphistaUpdated 2024-09-19
Download on Hugging Face
Parameters1.54B
Context4K
Layers28
Architectureqwen2
Smallest quant0.4 GB
Quick answer

Qwen2.5 Math 1.5B Instruct needs about 1.5 GB of memory at IQ3_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.4 GB (IQ1_S) to 3.1 GB.

Qwen2.5 Math 1.5B Instruct – a small math‑focused instruction model

Qwen2.5 Math 1.5B Instruct is a 1.54‑billion‑parameter model tuned for mathematical reasoning in English and Chinese. It supports Chain‑of‑Thought and Tool‑integrated Reasoning. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.

Good at

  • Math problem solving
  • Tool‑integrated reasoning
  • English and Chinese math

Limits

  • No vision support
  • Requires 8‑k context
  • License is Apache‑2.0

Best for

  • Chat‑based math tutoring
  • Math competition prep
  • Symbolic computation scripts

Who it’s for. Developers and researchers needing a lightweight math LLM for chat or few‑shot inference. The model is suitable for fine‑tuning on domain‑specific math tasks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.4 GB 1.1 GB
Fits Get file →
IQ1_M0.5 GB 1.1 GB
Fits Get file →
IQ2_XXS0.5 GB 1.1 GB
Fits Get file →
IQ2_XS0.6 GB 1.2 GB
Fits Get file →
IQ2_S0.6 GB 1.2 GB
Fits Get file →
IQ2_M0.6 GB 1.2 GB
Fits Get file →
Q2_K_S0.6 GB 1.3 GB
Fits Get file →
IQ3_XXS0.7 GB 1.3 GB
Fits Get file →
Q2_K0.7 GB 1.3 GB
Fits Get file →
IQ3_XS0.7 GB 1.3 GB
Fits Get file →
Q3_K_S0.8 GB 1.4 GB
Fits Get file →
IQ3_S0.8 GB 1.4 GB
Fits Get file →
IQ3_M0.8 GB 1.4 GB
Fits Get file →
Q3_K0.8 GB 1.4 GB
Fits Get file →
Q3_K_L0.9 GB 1.5 GB
Fits Get file →
IQ4_XS0.9 GB 1.5 GB
Fits Get file →
IQ4_NL0.9 GB 1.6 GB
Fits Get file →
Q4_K_S0.9 GB 1.6 GB
Fits Get file →
Q4_K1.0 GB 1.6 GB
Fits Get file →
Q5_K_S1.1 GB 1.7 GB
Fits Get file →
Q5_K1.1 GB 1.7 GB
Fits Get file →
Q6_K1.3 GB 1.9 GB
Fits Get file →
Q8_01.6 GB 2.3 GB
Fits Get file →
BF163.1 GB 3.7 GB
Fits Get file →
—3.1 GB 3.7 GB
Fits Get file →

For 8‑GB VRAM, use IQ2_XS (0.55 GB) or Q2_K_S (0.64 GB). For 16‑GB VRAM, Q3_K (0.82 GB) or Q4_K (0.99 GB) provide a good balance of size and performance. Larger quants such as Q8_0 (1.65 GB) give higher precision but need more memory.

What GPU do you need for Qwen2.5 Math 1.5B Instruct?

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 BF16 (3.1 GB file, about 3.8 GB in use).

Which Qwen2.5 Math 1.5B Instruct quant should you choose?

IQ3_M (0.8 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 0.4 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
Parameters1.54B
Layers28
Trained context4,096 tokens
KV cache (fp16)28 KB per token

Source

Quantized bylegraphista
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,162
Last updated2024-09-19

Frequently asked questions about Qwen2.5 Math 1.5B Instruct

How much VRAM does Qwen2.5 Math 1.5B Instruct need?

About 1.5 GB at IQ3_M with an 8K context window. That is the 0.8 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 Qwen2.5 Math 1.5B Instruct on an 8 GB GPU?

Yes, with BF16: the 3.1 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen2.5 Math 1.5B Instruct GGUF?

It depends on the quant: IQ1_S is 0.4 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.5 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.6 GB, IQ2_M is 0.6 GB and 19 more.

What context length does Qwen2.5 Math 1.5B Instruct support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.1 GB at 4K.

Where can I download Qwen2.5 Math 1.5B Instruct GGUF?

The files are on Hugging Face in the legraphista/Qwen2.5-Math-1.5B-Instruct-IMat-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 Qwen2.5 Math 1.5B Instruct 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 Qwen2.5 Math 1.5B Instruct on 8 GB VRAM?

Yes, using a quant like IQ2_XS or Q2_K_S will fit within 8 GB VRAM with an estimated memory usage of about 1.2–1.3 GB at 8k context.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen2.5-Math-1.5B-Instruct

Similar models

Browse all →

More from legraphista

All by legraphista →

More Qwen models

All Qwen →

Other tiny models

All tiny models →