[!TIP] Support this work → · X · GitHub · REAP paper · Cerebras REAP

Qwen3.6-35B-GGUF

GGUF quantization of Qwen/Qwen3.6-35B-A3B.

At a glance


Base model	Qwen/Qwen3.6-35B-A3B
Format	GGUF
Total params	35B
Active / token	3B
Experts / layer	—
Layers	—
Hidden size	—
Context	—
On-disk size	171 GB

Which variant should I pick?

Variant	Format	Link
`Qwen3.6-28B`	BF16	link
`Qwen3.6-28B-GGUF`	GGUF	link
`Qwen3.6-35B-GGUF` (this)	GGUF	link

Dynamic mixed-precision GGUF quantizations of Qwen/Qwen3.6-35B-A3B, produced and benchmarked on a Framework Desktop with AMD Ryzen AI MAX+ 395 (Radeon 8060S, gfx1151, 128 GB UMA) running Vulkan via llama.cpp.

Variants

File	Size	prefill (t/s)	decode (t/s)	Notes
`Qwen3.6-35B-A3B-Q8_0.gguf`	35 GB	975	52.7	near-lossless reference
`Qwen3.6-35B-A3B-Q6_K.gguf`	27 GB	830	62.2
`Qwen3.6-35B-A3B-Q5_K_M.gguf`	24 GB	943	64.1
`Qwen3.6-35B-A3B-Q4_K_M.gguf`	20 GB	1021	70.2	production sweet spot
`Qwen3.6-35B-A3B-Q4_0.gguf`	19 GB	1061	76.5	fastest decode
`Qwen3.6-35B-A3B-IQ4_NL.gguf`	19 GB	891	73.1
`Qwen3.6-35B-A3B-DYNAMIC.gguf`	19 GB	1100	64.0	fastest prefill; mixed per-tensor quant

All numbers: pp=4096 tokens, tg=128 tokens; -fa 1 -ctk q8_0 -ctv q8_0 -ub 2048 -b 2048 on a single Vulkan gfx1151 device.

Dynamic mix recipe

DYNAMIC.gguf uses a per-tensor quantization map chosen for the hybrid Gated DeltaNet + Gated Attention architecture:

attn_k / attn_q / attn_v → Q8_0 (retrieval-critical)
attn_output → Q5_K
ffn_gate_inp (router) → Q8_0 (routing-critical)
ffn_gate_exps / ffn_up_exps / ffn_down_exps (256 routed experts) → IQ4_NL
ffn_gate_shexp / ffn_up_shexp / ffn_down_shexp (shared expert) → Q6_K
token_embd / output → Q8_0
everything else → Q4_K_M (fallback)

Usage

llama-bench -m Qwen3.6-35B-A3B-DYNAMIC.gguf -ngl 99 -fa 1 -ctk q8_0 -ctv q8_0 \
  -ub 2048 -b 2048 -p 4096 -n 128

Benchmark context

Research series on pushing Qwen3.5/3.6 on AMD Strix Halo. Methodology, scripts, and live results: see the benchmark site referenced from the GitHub repo.

License

Apache 2.0 (inherited from base model).

License & citation

License inherited from the base model.

@misc{lasby2025reap,
  title  = {REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
  author = {Mike Lasby and Ivan Lazarevich and Nish Sinnadurai and Sean Lie and Yani Ioannou and Vithursan Thangarasa},
  year   = {2025}, eprint = {2510.13999}, archivePrefix = {arXiv}
}

0xSero/Qwen3.6-35B-GGUF