MI

MiroThinker 1.7

MirothinkerGGUF by mradermacherUpdated 2026-04-06
Download on Hugging Face
Parameters235B
Context256K
Layers94
Architectureqwen3moe
Smallest quant0.5 GB
Quick answer

MiroThinker 1.7 needs about 144.2 GB of memory at Q4_K_M (a 142.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.5 GB to 193.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.

MiroThinker 1.7 – 235B‑parameter Qwen3MOE model with 256K context

MiroThinker 1.7 is a 235B‑parameter Qwen3MOE model with a 262144‑token context window. It supports long‑horizon reasoning and up to 300 tool calls per task. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.

Good at

  • Long‑chain reasoning
  • Tool‑augmented agentic tasks
  • Deep multi‑step analysis

Limits

  • No vision support
  • Requires large VRAM for high‑quality quants
  • License is Apache‑2.0

Best for

  • Research agents needing 256K context
  • Complex tool‑based workflows
  • Long‑horizon decision making

Who it’s for. Researchers and developers building agentic systems that require extended context and multi‑step reasoning. The model is suited for environments where 8‑bit or higher precision is acceptable and where the Apache‑2.0 license is compatible with the project.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.5 GB 2.6 GB
Fits Get file →
IQ1_S47.9 GB 50.0 GB
Too big Get file →
IQ1_M53.1 GB 55.2 GB
Too big Get file →
IQ2_XXS61.8 GB 63.9 GB
Too big Get file →
IQ2_XS68.8 GB 70.9 GB
Too big Get file →
IQ2_S70.2 GB 72.3 GB
Too big Get file →
IQ2_M77.2 GB 79.2 GB
Too big Get file →
Q2_K_S79.8 GB 81.8 GB
Too big Get file →
Q2_K85.7 GB 87.8 GB
Too big Get file →
IQ3_XXS90.4 GB 92.5 GB
Too big Get file →
IQ3_XS96.0 GB 98.0 GB
Too big Get file →
Q3_K_S101.4 GB 103.5 GB
Too big Get file →
IQ3_S101.5 GB 103.5 GB
Too big Get file →
IQ3_M103.1 GB 105.1 GB
Too big Get file →
Q3_K_M112.4 GB 114.5 GB
Too big Get file →
Q3_K_L121.8 GB 123.9 GB
Too big Get file →
IQ4_XS125.3 GB 127.4 GB
Too big Get file →
Q4_0133.1 GB 135.2 GB
Too big Get file →
Q4_K_S133.7 GB 135.8 GB
Too big Get file →
Q4_K_M142.2 GB 144.2 GB
Too big Get file →
Q4_1147.2 GB 149.3 GB
Too big Get file →
Q5_K_S161.9 GB 164.0 GB
Too big Get file →
Q5_K_M166.8 GB 168.9 GB
Too big Get file →
Q6_K193.0 GB 195.1 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (47.95 GB file, 50 GB memory at 8K context). For 16‑GB VRAM, IQ2_XS (68.82 GB file, 70.9 GB memory) or Q2_K_S (79.76 GB file, 81.8 GB memory). For 32‑GB VRAM, Q4_K_M (142.15 GB file, 144.2 GB memory) or Q5_K_S (161.88 GB file, 164 GB memory). Memory estimates are approximate.

What GPU do you need for MiroThinker 1.7?

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 (0.5 GB file, about 2.6 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.6 GB in use).

Which MiroThinker 1.7 quant should you choose?

Q4_K_M is the usual starting point for MiroThinker 1.7: it balances file size and quality well. Here it is a 142.2 GB file.

If memory is tight, the smallest file is the first one in the table at 0.5 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

Architectureqwen3moe
Parameters235B (approximate, mixture of experts)
Layers94
Trained context262,144 tokens
KV cache (fp16)188 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)2,152
Last updated2026-04-06

Frequently asked questions about MiroThinker 1.7

How much VRAM does MiroThinker 1.7 need?

About 144.2 GB at Q4_K_M with an 8K context window. That is the 142.2 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 1.7 on an 8 GB GPU?

Yes, with the smaller files: the 0.5 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiroThinker 1.7 GGUF?

It depends on the quant: file is 0.5 GB, IQ1_S is 47.9 GB, IQ1_M is 53.1 GB, IQ2_XXS is 61.8 GB, IQ2_XS is 68.8 GB, IQ2_S is 70.2 GB and 18 more.

What context length does MiroThinker 1.7 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.3 GB at 32K.

Where can I download MiroThinker 1.7 GGUF?

The files are on Hugging Face in the mradermacher/MiroThinker-1.7-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 MiroThinker 1.7 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 MiroThinker 1.7 on 8 GB VRAM?

Use the IQ1_S quant. It requires about 50 GB of VRAM at 8K context, which is beyond 8 GB, so it is not feasible on 8 GB VRAM.

Does MiroThinker 1.7 support vision tasks?

No, the model does not have vision capabilities.

Other GGUFs of MiroThinker-1.7

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mirothinker models

All Mirothinker →

Other large models

All large models →