QW

MiroThinker-v1.0-8B

QwenGGUF by MungertUpdated 2025-11-18
Download on Hugging Face
Parameters8.2B
Context256K
Layers36
Architectureqwen3
Smallest quant0.0 GB
Quick answer

MiroThinker-v1.0-8B needs about 7.2 GB of memory at Q4_K_M (a 5.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 16.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

MiroThinker‑v1.0‑8B – 8.2B‑parameter Qwen3‑based agent model

MiroThinker‑v1.0‑8B is an 8.2B‑parameter Qwen3‑derived model focused on tool‑augmented reasoning. It supports a 256K context window and up to 600 tool calls per task. The model is released under the MIT license and is available in multiple GGUF quantizations.

Good at

  • Long‑horizon reasoning
  • Deep multi‑step analysis
  • Tool‑augmented agent tasks

Limits

  • No vision support
  • Requires 8.2B‑parameter model for full capability
  • Large context length demands high VRAM

Best for

  • Research agents needing deep reasoning
  • Tool‑integrated workflows
  • Long‑form dialogue with extended context

Who it’s for. Developers and researchers building agent systems that require extensive context handling and tool integration. The model is suitable for those who need a large‑parameter LLM with interactive scaling capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
IQ2_XXS2.9 GB 4.6 GB
Fits Get file →
IQ2_XS3.1 GB 4.8 GB
Fits Get file →
IQ2_S3.2 GB 4.9 GB
Fits Get file →
Q2_K_S3.2 GB 4.9 GB
Fits Get file →
IQ2_M3.3 GB 5.0 GB
Fits Get file →
Q2_K_M3.4 GB 5.1 GB
Fits Get file →
IQ3_XXS3.8 GB 5.5 GB
Fits Get file →
IQ3_XS3.9 GB 5.6 GB
Fits Get file →
Q3_K_S4.2 GB 5.9 GB
Fits Get file →
IQ3_M4.2 GB 5.9 GB
Fits Get file →
Q3_K_M4.3 GB 6.0 GB
Fits Get file →
IQ4_NL4.6 GB 6.3 GB
Fits Get file →
IQ4_XS4.7 GB 6.4 GB
Fits Get file →
Q4_K_S5.0 GB 6.7 GB
Fits Get file →
Q4_15.2 GB 6.9 GB
Fits Get file →
Q4_05.2 GB 6.9 GB
Fits Get file →
Q4_K_M5.4 GB 7.2 GB
Fits Get file →
Q5_06.1 GB 7.8 GB
Tight Get file →
Q5_K_M6.3 GB 8.0 GB
Tight Get file →
Q5_16.5 GB 8.2 GB
Too big Get file →
Q6_K_M7.0 GB 8.7 GB
Too big Get file →
Q8_08.7 GB 10.4 GB
Too big Get file →
F1612.3 GB 14.0 GB
Too big Get file →
BF1616.4 GB 18.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 5.45 GB, estimated 7.2 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (6.25 GB, 8 GB memory) or Q5_0 (6.1 GB, 7.8 GB). For 16 GB VRAM, Q6_K_M (7.03 GB, 8.7 GB) or Q8_0 (8.71 GB, 10.4 GB).

What GPU do you need for MiroThinker-v1.0-8B?

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 the main file (0.0 GB file, about 1.7 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (6.3 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
  • 16 GB VRAM: the best quant that fits is F16 (12.3 GB file, about 14.0 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (16.4 GB file, about 18.1 GB in use).

Which MiroThinker-v1.0-8B quant should you choose?

Q4_K_M is the usual starting point for MiroThinker-v1.0-8B: it balances file size and quality well. Here it is a 5.4 GB file.

The Q8_0 file is 8.7 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters8.2B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized byMungert
FamilyQwen
Base modelQwen/Qwen3-8B
Licensemit
Downloads (HF)1,759
Last updated2025-11-18

Frequently asked questions about MiroThinker-v1.0-8B

How much VRAM does MiroThinker-v1.0-8B need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.4 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 MiroThinker-v1.0-8B on an 8 GB GPU?

Yes, with Q5_K_M: the 6.3 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiroThinker-v1.0-8B GGUF?

It depends on the quant: file is 0.0 GB, IQ2_XXS is 2.9 GB, IQ2_XS is 3.1 GB, IQ2_S is 3.2 GB, Q2_K_S is 3.2 GB, IQ2_M is 3.3 GB and 19 more.

What context length does MiroThinker-v1.0-8B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download MiroThinker-v1.0-8B GGUF?

The files are on Hugging Face in the Mungert/MiroThinker-v1.0-8B-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 MiroThinker-v1.0-8B use?

Hugging Face lists the license as mit. 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 MiroThinker‑v1.0‑8B on 8 GB VRAM?

Yes, with the Q4_K_M quantization the model requires about 7.2 GB of VRAM at 8 k context.

Does the model support vision inputs?

No, MiroThinker‑v1.0‑8B does not include vision capabilities.

What license applies to this model?

The model is released under the MIT license.

Other GGUFs of Qwen3-8B

Similar models

Browse all →

More from Mungert

All by Mungert →

More Qwen models

All Qwen →

Other small models

All small models →