Run unsloth/Qwen-AgentWorld-35B-A3B-GGUF locally

License: apache-2.0 ⬇ 377,256 ❤ 156
Parameters34.66B
Context262,144

unsloth/Qwen-AgentWorld-35B-A3B-GGUF is a very large language model with 34.66 billion parameters, built on the qwen35moe architecture. It is released under the apache-2.0 license and has been downloaded 377,256 times.

To run unsloth/Qwen-AgentWorld-35B-A3B-GGUF locally at a 4,096-token context, its quantized versions need between 11.66 GB (IQ2_XXS, lowest quality) and 65.57 GB (BF16, highest quality) of memory, weights plus KV cache and a system margin included.

For most users the best balance is Q4_K_XL, needing about 21.75 GB. That means unsloth/Qwen-AgentWorld-35B-A3B-GGUF fits entirely in the VRAM of a 12 GB GPU or larger, running fully on the GPU.

→ Guide: How much VRAM do you need?

All quantizations

Quant.Bits QualityWeights KVTotal Speed~Verdict
IQ2_XXS 2.65 Low 10.71 GB 0.16 GB 11.66 GB 4.7 t/s Offload
IQ2_M 2.67 Low 10.77 GB 0.16 GB 11.73 GB 4.6 t/s Offload
Q2_K_XL 2.83 Low 11.41 GB 0.16 GB 12.37 GB 4.4 t/s Offload
IQ3_XXS 3.17 Low 12.8 GB 0.16 GB 13.76 GB 3.9 t/s Offload
IQ3_S 3.46 Fair 13.96 GB 0.16 GB 14.91 GB 3.6 t/s Offload
Q3_K_M 3.85 Fair 15.53 GB 0.16 GB 16.49 GB 3.2 t/s Offload
Q3_K_XL 3.88 Fair 15.65 GB 0.16 GB 16.61 GB 3.2 t/s Offload
IQ4_XS 4.1 Fair 16.56 GB 0.16 GB 17.52 GB 3.0 t/s Offload
IQ4_NL 4.18 Fair 16.87 GB 0.16 GB 17.82 GB 3.0 t/s Offload
Q4_K_S 4.82 Good 19.46 GB 0.16 GB 20.41 GB 2.6 t/s Offload
GGUF 5.0 Very good 20.18 GB 0.16 GB 21.14 GB 2.5 t/s Offload
Q4_K_M 5.11 Very good 20.61 GB 0.16 GB 21.57 GB 2.4 t/s Offload
Q4_K_XL 5.15 Very good 20.79 GB 0.16 GB 21.75 GB 2.4 t/s Offload
Q5_K_S 5.76 Very good 23.23 GB 0.16 GB 24.19 GB Insufficient
Q5_K_M 6.11 Very good 24.64 GB 0.16 GB 25.6 GB Insufficient
Q5_K_XL 6.12 Very good 24.71 GB 0.16 GB 25.66 GB Insufficient
Q6_K 6.76 Excellent 27.3 GB 0.16 GB 28.25 GB Insufficient
Q6_K_XL 7.35 Excellent 29.66 GB 0.16 GB 30.61 GB Insufficient
Q8_0 8.52 Excellent 34.37 GB 0.16 GB 35.32 GB Insufficient
Q8_K_XL 8.82 Excellent 35.58 GB 0.16 GB 36.53 GB Insufficient
BF16 16.01 Excellent 64.61 GB 0.16 GB 65.57 GB Insufficient

KV cache computed from the model's exact architecture. Speed is a rough estimate bounded by memory bandwidth.

Frequently asked questions

How much VRAM do you need to run unsloth/Qwen-AgentWorld-35B-A3B-GGUF?

You need about 11.73 GB of VRAM to run unsloth/Qwen-AgentWorld-35B-A3B-GGUF entirely on the GPU using the IQ2_M quantization (at a 4,096-token context). Smaller quantizations lower the requirement at the cost of quality.

Can I run unsloth/Qwen-AgentWorld-35B-A3B-GGUF on an 8 GB GPU?

Partially. unsloth/Qwen-AgentWorld-35B-A3B-GGUF only fits on an 8 GB GPU by offloading part of it to system RAM (with Q4_K_XL), which runs but is slower.

Can I run unsloth/Qwen-AgentWorld-35B-A3B-GGUF on a 16 GB GPU?

Yes. With 16 GB of VRAM you can run unsloth/Qwen-AgentWorld-35B-A3B-GGUF fully on the GPU using IQ3_S (about 14.91 GB).

Can I run unsloth/Qwen-AgentWorld-35B-A3B-GGUF on a 24 GB GPU?

Yes. With 24 GB of VRAM you can run unsloth/Qwen-AgentWorld-35B-A3B-GGUF fully on the GPU using Q4_K_XL (about 21.75 GB).

What is the best quantization for unsloth/Qwen-AgentWorld-35B-A3B-GGUF?

If memory allows, higher bits-per-weight means better quality. A common sweet spot is a Q4_K_M or Q5_K_M quantization, which keeps most of the quality while roughly halving the memory versus 8-bit. Pick the highest quantization that still fits in your VRAM.