Repo	GGUF Equivalent	Size	Decode (tok/s)
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q2_K_XL-mlx	UD-Q2_K_XL	14 GB	63.7
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q3_K_XL-mlx	UD-Q3_K_XL	18 GB	59.2
Brooooooklyn/Qwen3.6-35B-A3B-UD-MXFP4_K_XL-mlx	—	21 GB	54.4
Brooooooklyn/Qwen3.6-35B-A3B-UD-NVFP4_K_XL-mlx	—	22 GB	59.1
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q4_K_XL-mlx	UD-Q4_K_XL	22 GB	55.1
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q5_K_XL-mlx (this model)	UD-Q5_K_XL	26 GB	51.8
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q6_K_XL-mlx	UD-Q6_K_XL	31 GB	54.4
Brooooooklyn/Qwen3.6-35B-A3B-UD-MXFP8_K_XL-mlx	—	35 GB	47.6
Brooooooklyn/Qwen3.6-35B-A3B-UD-Q8_K_XL-mlx	UD-Q8_K_XL	36 GB	45.9

Benchmarked on Apple M3 Max 128GB via examples/lm.ts (best decode tok/s across turns 2–4, steady-state).

Performance

Steady-state decode: 51.8 tok/s on Apple M3 Max 128GB (best of turns 2–4, examples/lm.ts capitals chat with reasoningEffort: 'low').

Decode is memory-bandwidth bound on Apple Silicon — fewer bytes per token directly translates to higher throughput. The MoE architecture activates only 8 of 256 experts per token (~3B active out of 35.9B total), and the compiled C++ forward graph fuses the per-layer dispatch.

Per-Tensor Bit Assignments (N=5)

Weight	Bits	Rationale
`embed_tokens`	8-bit	KLD ~0.15 — very low sensitivity
`lm_head`	8-bit	KLD ~0.05 — safest tensor
`self_attn.q/k/v_proj`	8-bit + AWQ	KLD ~1.5–2.9, AWQ via layernorm
`linear_attn.in_proj_qkv/z`	8-bit + AWQ	KLD ~2.9, AWQ via layernorm
`self_attn.o_proj`	bf16	NOT AWQ-correctable
`linear_attn.out_proj`	bf16	KLD ~6.0 — worst tensor
`down_proj`	6-bit	"Slightly more sensitive"
`gate_proj`, `up_proj`	5-bit	base bits
Router gates	8-bit	MoE routing accuracy
GDN params (A_log, etc)	bf16	State-space dynamics

Quantization Strategy

Based on Unsloth Dynamic 2.0 per-tensor KLD analysis. Sensitive layers get higher bits with AWQ correction, while the bulk of FFN expert weights are aggressively quantized. imatrix AWQ pre-scaling amplifies important weight channels and fuses inverse scales into preceding layer norms (zero inference overhead).

AWQ-correctable projections (q/k/v, in_proj_qkv/z) are quantized at 8-bit via input_layernorm. Non-AWQ-correctable projections (o_proj, out_proj) are kept at bf16 — their inputs come from attention/GDN computation, not from a norm layer.

Architecture

Parameter	Value
Total parameters	35.9B (3B active per token)
Hidden size	2,048
Layers	40 (30 linear + 10 full attention)
Attention heads	16 (2 KV heads, GQA 8:1)
Head dimension	256
Experts	256 per MoE layer, top-8 routing
Vocab size	248,320
Max context	262,144 tokens

Usage

typescript

import { loadSession } from '@mlx-node/lm';

const session = await loadSession('./Qwen3.6-35B-A3B-UD-Q5_K_XL-mlx');

for await (const event of session.sendStream('Explain the hybrid attention mechanism in Qwen3.6.', {
  config: { maxNewTokens: 2048, temperature: 0.6, reasoningEffort: 'low' },
})) {
  if (!event.done) process.stdout.write(event.text);
}

How It Was Made

bash

mlx convert \
  -i Qwen3.6-35B-A3B \
  -o Qwen3.6-35B-A3B-UD-Q5_K_XL-mlx \
  -q --q-bits 5 --q-recipe unsloth \
  --imatrix-path imatrix_unsloth.gguf

Acknowledgments

Unsloth — Quantization strategy based on their per-layer KLD benchmarks and Dynamic 2.0 methodology
Qwen Team — For the Qwen3.6 model family
Apple MLX — For the Metal-accelerated ML framework

License

Apache 2.0 (inherited from base model).

Brooooooklyn/Qwen3.6-35B-A3B-UD-Q5_K_XL-mlx

Qwen3.6-35B-A3B — UD-Q5_K_XL (mlx-node)

All Variants