QW

Qwen3.5 2B multiharness RL

QwenGGUF by igorktechUpdated 2026-10-15
Download on Hugging Face
Parameters1.88B
Context256K
Layers24
Architectureqwen35
Smallest quant1.0 GB
Quick answer

Qwen3.5 2B multiharness RL needs about 2.2 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 9 quants, from 1.0 GB (Q2_K) to 2.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Qwen3.5 2B multiharness RL – a 1.88B parameter model fine‑tuned for agentic tasks

Qwen3.5 2B multiharness RL is a 1.88B parameter model trained with asynchronous GRPO on OpenCode, Claude Code, Codex, and Mini‑SWE‑Agent. It supports reasoning, tools, and vision. The model is released under Apache‑2.0 and available in multiple GGUF quantizations.

Good at

  • Reasoning and tool use
  • Vision input handling
  • Agentic data‑analysis tasks

Limits

  • No official vision benchmark
  • Requires 8k context for memory estimates
  • No image‑generation capability

Best for

  • Chatbot agents needing tool calls
  • Data‑analysis workflows
  • Vision‑enabled text tasks

Who it’s for. Developers building agentic applications that require reasoning, tool use, and basic vision. The model is suitable for research and production use under the Apache‑2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.0 GB 1.9 GB
Fits Get file →
IQ3_M1.1 GB 2.0 GB
Fits Get file →
Q3_K_M1.1 GB 2.0 GB
Fits Get file →
IQ4_XS1.2 GB 2.1 GB
Fits Get file →
Q4_K_S1.2 GB 2.1 GB
Fits Get file →
Q4_K_M1.3 GB 2.2 GB
Fits Get file →
Q5_K_M1.4 GB 2.3 GB
Fits Get file →
Q6_K1.6 GB 2.5 GB
Fits Get file →
Q8_02.0 GB 2.9 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (1.27 GB) or Q5_K_M (1.41 GB) are good choices, using about 2.2–2.3 GB of VRAM at 8k context. For 4 GB VRAM, Q3_K_M (1.1 GB) or IQ3_M (1.06 GB) provide the best balance, using roughly 2 GB of VRAM. Larger models like Q8_0 (2.01 GB) need 2.9 GB VRAM and are suitable for high‑memory systems.

What GPU do you need for Qwen3.5 2B multiharness RL?

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 Q8_0 (2.0 GB file, about 2.9 GB in use).

Which Qwen3.5 2B multiharness RL quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 2B multiharness RL: it balances file size and quality well. Here it is a 1.3 GB file.

The Q8_0 file is 2.0 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 Q2_K at 1.0 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
Parameters1.88B
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized byigorktech
FamilyQwen
Licenseapache-2.0
Downloads (HF)844
Last updated2026-10-15

Frequently asked questions about Qwen3.5 2B multiharness RL

How much VRAM does Qwen3.5 2B multiharness RL need?

About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Qwen3.5 2B multiharness RL on an 8 GB GPU?

Yes, with Q8_0: the 2.0 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5 2B multiharness RL GGUF?

It depends on the quant: Q2_K is 1.0 GB, IQ3_M is 1.1 GB, Q3_K_M is 1.1 GB, IQ4_XS is 1.2 GB, Q4_K_S is 1.2 GB, Q4_K_M is 1.3 GB and 3 more.

What context length does Qwen3.5 2B multiharness RL 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 1.6 GB at 32K.

Where can I download Qwen3.5 2B multiharness RL GGUF?

The files are on Hugging Face in the igorktech/Qwen3.5-2B-multiharness-RL-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 Qwen3.5 2B multiharness RL 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 Qwen3.5 2B multiharness RL on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_M quantizations will fit within 8 GB VRAM, with estimated usage around 2.2–2.3 GB at 8k context.

Does this model support vision tasks?

The model includes a vision projector, but the release has no official vision benchmark. It is primarily tuned for text and tool use.

What license applies to this model?

The model is released under the Apache License 2.0, derived from Qwen/Qwen3.5-2B and FineEnvs reinforcement‑learning fine‑tune.

Similar models

Browse all →

More Qwen models

All Qwen →

Other tiny models

All tiny models →