<!-- Markdown mirror of https://getrigbase.com/models/qwen3-5-35b-a3b/ . Source of truth is the HTML page. Data licence: CC BY 4.0, please cite RigBase (https://getrigbase.com/models/qwen3-5-35b-a3b/). -->
Source: https://getrigbase.com/models/qwen3-5-35b-a3b/
Last updated: 2026-11-21

[Models](https://getrigbase.com/models/) / Qwen3.5 35B-A3B

# Best home rig for Qwen3.5 35B-A3B

Quick answer

**How much VRAM does Qwen3.5 35B-A3B need?**
The weights are about 22.0 GB at Q4_K_M (35.95B params × 4.89 bits ÷ 8, before context/KV cache). Add memory for context (KV cache) and the runtime.

**What is the fastest measured hardware for Qwen3.5 35B-A3B?**
ThinkPad X1 Carbon Gen 13 (Core Ultra 7 258V, Arc 140V iGPU, 32 GB): Qwen3.5 35B-A3B IQ4_XS at 25.6 tok/s on llama.cpp Vulkan, 22.3 at 8K depth: 25.58 tok/s generation (llama.cpp 12377 Vulkan (Mesa ANV), IQ4_XS (16.95 GiB)), from https://github.com/ggml-org/llama.cpp/discussions/10879.

Last updated: 21 Nov 2026

Legacy model 35.95B total · 3B active 4 measured results fastest plain decode: 25.58 tok/s  [model info ↗](https://huggingface.co/Qwen/Qwen3.5-35B-A3B)

**Newer model available: [Qwen3.6 35B-A3B](https://getrigbase.com/models/qwen3-6-35b-a3b/)**. Qwen3.5 35B-A3B is a legacy model; its numbers stay here for reference. same-size Qwen MoE, newer release. [source ↗](https://huggingface.co/Qwen/Qwen3.6-35B-A3B)

Real, measured generation speeds for Qwen3.5 35B-A3B on home hardware, fastest first. Different quants/engines aren't directly comparable.

| Build | Quant | Engine | tok/s | Prompt processing (tok/s) | Cost | Source |
|---|---|---|---|---|---|---|
| [ThinkPad X1 Carbon Gen 13 (Core Ultra 7 258V, Arc 140V iGPU, 32 GB): Qwen3.5 35B-A3B IQ4_XS at 25.6 tok/s on llama.cpp Vulkan, 22.3 at 8K depth](https://getrigbase.com/builds/thinkpad-x1-carbon-gen13-arc-140v-lunar-lake-qwen35-35b-a3b-vulkan/) | IQ4_XS (16.95 GiB) | llama.cpp 12377 Vulkan (Mesa ANV) | **25.58** | 379 @8192 · est. TTFT @8k ≈21.6 s* |  | [github.com ↗](https://github.com/ggml-org/llama.cpp/discussions/10879) |
| [Radeon 890M iGPU (Ryzen AI 9 HX 370): Qwen3.5 35B-A3B Q4_K_M at 24.8 tok/s on llama.cpp Vulkan b10830, 20.3 on b12387 (tg regression report)](https://getrigbase.com/builds/radeon-890m-ryzen-ai-9-hx-370-qwen35-35b-a3b-vulkan-b10830-vs-b12387/) | Unsloth UD-Q4_K_M | llama.cpp b10830 465e49b9c (Vulkan, RADV) | **24.8** | 251 @512 · est. TTFT @8k ≈32.6 s* |  | [github.com ↗](https://github.com/ggml-org/llama.cpp/issues/32290) |
| [NVIDIA Jetson AGX Xavier 32 GB (Volta SM72): LFM2.5 24B-A2B Q4_K_M at 36.9 tok/s and Qwen3.5 35B-A3B Q4_K_M at 24.6 on llama.cpp v1.0.0 CUDA](https://getrigbase.com/builds/jetson-agx-xavier-32gb-lfm25-24b-a2b-qwen35-35b-a3b-llamacpp-v1-cuda-sm72/) | Q4_K_M (20.21 GiB) | llama.cpp v1.0.0 11fe021 (CUDA 11.4, SM72) | **24.6** | 228 @512 · est. TTFT @8k ≈35.9 s* |  | [github.com ↗](https://github.com/ggml-org/llama.cpp/issues/32511) |
| [Radeon 890M iGPU (Ryzen AI 9 HX 370): Qwen3.5 35B-A3B Q4_K_M at 24.8 tok/s on llama.cpp Vulkan b10830, 20.3 on b12387 (tg regression report)](https://getrigbase.com/builds/radeon-890m-ryzen-ai-9-hx-370-qwen35-35b-a3b-vulkan-b10830-vs-b12387/) | Unsloth UD-Q4_K_M | llama.cpp b12387 a956a852c (Vulkan, RADV) | **20.32** | 293 @512 · est. TTFT @8k ≈28.0 s* |  | [github.com ↗](https://github.com/ggml-org/llama.cpp/issues/32290) |

Prompt processing = prefill speed reported by the source, @ prompt length. * est. TTFT @8k is calculated from measured prefill, not measured. [Why it matters](https://getrigbase.com/can-it-run/#prefill).
Ad · this space is available **Sponsor this spot: reach people building local AI rigs.** One clearly-labeled slot per page, no tracking scripts.  [Sponsor this spot →](https://getrigbase.com/advertise/#inquiry)

**Rent before you buy:** try this model on a cloud GPU for a few dollars first: [Runpod](https://runpod.io?ref=77qcpl2c) (referral link; sign up with Google to get the new-user bonus)

## Memory math: how much VRAM / RAM does Qwen3.5 35B-A3B need?

Qwen3.5 35B-A3B has **35.95B parameters**, about **3B active** per token ([source](https://huggingface.co/Qwen/Qwen3.5-35B-A3B): Qwen model card: 35B total / 3B activated MoE (8 routed + 1 shared experts), Apache 2.0, HF repo created 24 Feb 2026; HF safetensors total 35.95B (includes vision encoder)). Weight size = parameters × bits-per-weight ÷ 8, before context (KV cache) and runtime overhead.

| Format | Bits/weight | Weights | Smallest common memory size that holds the weights alone |
|---|---|---|---|
| Q8_0 | 8.50 | 38.2 GB | 48 GB |
| Q6_K | 6.56 | 29.5 GB | 32 GB |
| Q5_K_M | 5.70 | 25.6 GB | 32 GB |
| Q4_K_M | 4.89 | **22.0 GB** | 24 GB |
| Q3_K_M | 4.00 | 18.0 GB | 24 GB |
| Q2_K | 3.16 | 14.2 GB | 16 GB |

Bits-per-weight for GGUF quants are llama.cpp's own figures ([llama.cpp quantize README](https://github.com/ggml-org/llama.cpp/blob/master/tools/quantize/README.md)). "As measured" rows apply the source's stated bits-per-weight to the parameter count; real files differ slightly because some layers stay at higher precision. Try other combinations in the [VRAM calculator](https://getrigbase.com/can-it-run/).

**Why it can still run on smaller GPUs:** it is a mixture-of-experts model, so only about 3B of its 35.95B parameters are used for each generated token. Runtimes such as llama.cpp (--n-cpu-moe), ExLlamaV3 or Project Maya can keep most expert weights in system RAM and only the shared layers and hot experts in VRAM. Then you need **VRAM + system RAM ≥ weights**, and speed is limited mainly by RAM bandwidth.

## FAQ

### How much VRAM does Qwen3.5 35B-A3B need?

The weights are about 22.0 GB at Q4_K_M (35.95B params × 4.89 bits ÷ 8, before context/KV cache). Add memory for context (KV cache) and the runtime.

### What is the fastest measured hardware for Qwen3.5 35B-A3B?

ThinkPad X1 Carbon Gen 13 (Core Ultra 7 258V, Arc 140V iGPU, 32 GB): Qwen3.5 35B-A3B IQ4_XS at 25.6 tok/s on llama.cpp Vulkan, 22.3 at 8K depth: 25.58 tok/s generation (llama.cpp 12377 Vulkan (Mesa ANV), IQ4_XS (16.95 GiB)), from https://github.com/ggml-org/llama.cpp/discussions/10879.

Related: [what GPU do you need for 2026 models](https://getrigbase.com/guides/what-gpu-for-qwen3-6-gemma-4-gpt-oss/) · [all builds](https://getrigbase.com/builds/)
