Views
No views yet
| 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 |
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.| 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 |
-fa 1 -ctk q8_0 -ctv q8_0 -ub 2048 -b 2048 on a single Vulkan gfx1151 device.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_Kffn_gate_inp (router) → Q8_0 (routing-critical)ffn_gate_exps / ffn_up_exps / ffn_down_exps (256 routed experts) → IQ4_NLffn_gate_shexp / ffn_up_shexp / ffn_down_shexp (shared expert) → Q6_Ktoken_embd / output → Q8_01llama-bench -m Qwen3.6-35B-A3B-DYNAMIC.gguf -ngl 99 -fa 1 -ctk q8_0 -ctv q8_0 \
2 -ub 2048 -b 2048 -p 4096 -n 1281@misc{lasby2025reap,
2 title = {REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
3 author = {Mike Lasby and Ivan Lazarevich and Nish Sinnadurai and Sean Lie and Yani Ioannou and Vithursan Thangarasa},
4 year = {2025}, eprint = {2510.13999}, archivePrefix = {arXiv}
5}