QW

hishab qwen3.5 0.8b json full v10

QwenGGUF by ryuma007Updated 2026-10-17
Download on Hugging Face
Parameters752M
Context256K
Layers25
Architectureqwen35
Smallest quant0.5 GB
Quick answer

hishab qwen3.5 0.8b json full v10 needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 11 quants, from 0.5 GB (IQ3_M) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.

Hishab Qwen3.5 0.8B JSON model for Bangladeshi finance chat

Hishab Qwen3.5 0.8B JSON is a small on‑device language model fine‑tuned to extract transaction data from chat messages in English, Bangla, Banglish or mixed language. It returns a strict JSON array of transactions with fields description, amount, category and type.

Good at

  • JSON extraction from multilingual chat
  • Bangladeshi financial context
  • Reasoning and tool use

Limits

  • No vision support
  • Limited to 262144 context tokens
  • Requires exact system prompt

Best for

  • Personal finance apps
  • Chatbot transaction parsing
  • Data extraction pipelines

Who it’s for. Developers building local finance assistants for Bangladeshi users who need on‑device inference and strict JSON output. The model is suitable for prototyping and research use cases.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M0.5 GB 1.4 GB
Fits Get file →
Q3_K_M0.5 GB 1.4 GB
Fits Get file →
Q4_00.5 GB 1.4 GB
Fits Get file →
Q4_00.5 GB 1.4 GB
Fits Get file →
IQ4_XS0.5 GB 1.4 GB
Fits Get file →
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q5_K_M0.6 GB 1.5 GB
Fits Get file →
Q6_K0.6 GB 1.5 GB
Fits Get file →
Q8_00.8 GB 1.7 GB
Fits Get file →
F161.5 GB 2.4 GB
Fits Get file →

For 8 GB VRAM, use IQ3_M or Q3_K_M (file size 0.45–0.47 GB, memory 1.4 GB at 8k context). For 12 GB VRAM, Q5_K_M or Q6_K (0.58–0.63 GB, memory 1.5 GB). For 24 GB VRAM, F16 (1.52 GB, memory 2.4 GB).

What GPU do you need for hishab qwen3.5 0.8b json full v10?

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 (1.5 GB file, about 2.4 GB in use).

Which hishab qwen3.5 0.8b json full v10 quant should you choose?

Q4_K_M is the usual starting point for hishab qwen3.5 0.8b json full v10: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.8 GB, about 1.5 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 IQ3_M at 0.5 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

Architectureqwen35
Parameters752M
Layers25
Trained context262,144 tokens
KV cache (fp16)50 KB per token

Source

Quantized byryuma007
FamilyQwen
Licenseapache-2.0
Downloads (HF)838
Last updated2026-10-17

Frequently asked questions about hishab qwen3.5 0.8b json full v10

How much VRAM does hishab qwen3.5 0.8b json full v10 need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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 hishab qwen3.5 0.8b json full v10 on an 8 GB GPU?

Yes, with F16: the 1.5 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of hishab qwen3.5 0.8b json full v10 GGUF?

It depends on the quant: IQ3_M is 0.5 GB, Q3_K_M is 0.5 GB, Q4_0 is 0.5 GB, Q4_0 is 0.5 GB, IQ4_XS is 0.5 GB, Q4_K_M is 0.5 GB and 5 more.

What context length does hishab qwen3.5 0.8b json full v10 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.

Where can I download hishab qwen3.5 0.8b json full v10 GGUF?

The files are on Hugging Face in the ryuma007/hishab-qwen3.5-0.8b-json-full-v10-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 hishab qwen3.5 0.8b json full v10 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 this model on 8 GB VRAM?

Yes, using IQ3_M or Q3_K_M quantizations which require about 1.4 GB of VRAM at 8k context.

Does the model support vision inputs?

No, the model is a causal language model with no vision encoder.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Qwen3.5-0.8B

Similar models

Browse all →

More from ryuma007

All by ryuma007 →

More Qwen models

All Qwen →

Other tiny models

All tiny models →