QW

MiRL Qwen3.5 4B

QwenGGUF by mradermacherUpdated 2026-10-23
Download on Hugging Face
Parameters4.21B
Context256K
Layers33
Architectureqwen35
Smallest quant1.9 GB
Quick answer

MiRL Qwen3.5 4B needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 1.9 GB (Q2_K) to 8.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

MiRL Qwen3.5 4B – a 4.21B parameter Qwen model fine‑tuned for terminal agent tasks

MiRL Qwen3.5 4B is a 4.21B parameter language model based on Qwen3.5. It is fine‑tuned with reinforcement learning to reduce terminal agent misbehaviors. The model supports reasoning, tools, and vision capabilities.

Good at

  • Reasoning on complex prompts
  • Tool usage in terminal tasks
  • Vision‑enabled interactions

Limits

  • No vision or MTP weights included
  • Requires --language-model-only flag
  • License is apache-2.0

Best for

  • Terminal agent fine‑tuning
  • Debugging misbehaviors in RL agents
  • Testing vision‑enabled prompts

Who it’s for. Developers building terminal agents who need a model that has been trained to avoid common misbehaviors. Researchers interested in reinforcement learning for language models may also find this useful.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.9 GB 3.5 GB
Fits Get file →
Q3_K_S2.1 GB 3.7 GB
Fits Get file →
Q3_K_M2.3 GB 3.9 GB
Fits Get file →
Q3_K_L2.4 GB 4.0 GB
Fits Get file →
IQ4_XS2.5 GB 4.1 GB
Fits Get file →
Q4_K_S2.6 GB 4.2 GB
Fits Get file →
Q4_K_M2.7 GB 4.3 GB
Fits Get file →
Q5_K_S3.0 GB 4.6 GB
Fits Get file →
Q5_K_M3.1 GB 4.7 GB
Fits Get file →
Q6_K3.5 GB 5.1 GB
Fits Get file →
Q8_04.5 GB 6.1 GB
Fits Get file →
F168.4 GB 10.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 2.56 GB, estimated memory 4.2 GB at 8 k context). If 12 GB VRAM is available, Q5_K_M (file size 3.07 GB, estimated memory 4.7 GB) offers higher quality. For larger budgets, Q8_0 (file size 4.48 GB, estimated memory 6.1 GB) provides the best precision.

What GPU do you need for MiRL Qwen3.5 4B?

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 Q3_K_L (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.5 GB file, about 5.1 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (8.4 GB file, about 10.0 GB in use).

Which MiRL Qwen3.5 4B quant should you choose?

Q4_K_M is the usual starting point for MiRL Qwen3.5 4B: it balances file size and quality well. Here it is a 2.7 GB file.

The Q8_0 file is 4.5 GB, about 1.7 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 Q2_K at 1.9 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

Architectureqwen35
Parameters4.21B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)972
Last updated2026-10-23

Frequently asked questions about MiRL Qwen3.5 4B

How much VRAM does MiRL Qwen3.5 4B need?

About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 MiRL Qwen3.5 4B on an 8 GB GPU?

Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MiRL Qwen3.5 4B GGUF?

It depends on the quant: Q2_K is 1.9 GB, Q3_K_S is 2.1 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.4 GB, IQ4_XS is 2.5 GB, Q4_K_S is 2.6 GB and 6 more.

What context length does MiRL Qwen3.5 4B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.

Where can I download MiRL Qwen3.5 4B GGUF?

The files are on Hugging Face in the mradermacher/MiRL-Qwen3.5-4B-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 MiRL Qwen3.5 4B 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 MiRL Qwen3.5 4B on 8 GB VRAM?

Yes, the Q4_K_S quant uses about 4.2 GB of VRAM at 8 k context, which fits within an 8 GB budget.

Does this model include vision weights?

No, the GGUF files contain only the language model. Vision support requires separate weights.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of MiRL-Qwen3.5-4B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other small models

All small models →