Qwen3-Coder-Next 64B REAP - GGUF

Quantized GGUF versions of 0xSero/qwen3-coder-next-64b-REAP. These were generated using the default settings with llama-quantize (b8740).

Quantizations provided

File	Quantization	Size
`qwen3-coder-next-64b-REAP-Q4_K_M.gguf`	Q4_K_M	39.1 GB
`qwen3-coder-next-64b-REAP-Q5_K_M.gguf`	Q5_K_M	45.8 GB
`qwen3-coder-next-64b-REAP-Q6_K.gguf`	Q6_K	52.9 GB
`qwen3-coder-next-64b-REAP-Q8_0.gguf`	Q8_0	68.4 GB

I tested perplexity using llama-perplexity and Salesforce's wikitext-2-raw-v1.

File	Quantization	Ctx	PPL
`qwen3-coder-next-64b-REAP-Q4_K_M.gguf`	Q4_K_M	512	12.6123 +/- 0.10518
`qwen3-coder-next-64b-REAP-Q5_K_M.gguf`	Q5_K_M	512	12.5573 +/- 0.10461
`qwen3-coder-next-64b-REAP-Q6_K.gguf`	Q6_K	512	12.4087 +/- 0.10285
`qwen3-coder-next-64b-REAP-Q8_0.gguf`	Q8_0	512	12.4389 +/- 0.10323
`qwen3-coder-next-64b-REAP-BF16.gguf`	BF16	512	12.4162 +/- 0.10302

GGUF

Model size

64B params

Architecture

qwen3next

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Base model

Finetuned

Quantized

(1)

this model