Qwen3.5 4B

4B

Alibaba Qwen3.5

The 4B size of Qwen3.5, for 4 to 8 GB cards, base-model Macs and CPU-only machines. Only 8 of its 32 layers keep a growing KV cache. At Q4_K_M it needs about 3.3 GB at 4K context and 4.3 GB at 32K, so a 6 GB card is enough for long chats; its full 256K window needs about 12 GB. Reasoning is off by default on the small Qwen3.5 sizes, and it reads images through a separate vision encoder. Sizes come from the published GGUF file sizes, and no per-level quality loss has been published.

⬇ 7.9M HF downloads♥ 1040 likesQwen/Qwen3.5-4B· stats from 10/11/2026
Consumer GPUMac / Apple SiliconCPU / VPS

262K

Max Context

2

Quant Variants

GGUF Q8_0

Best Quality

—

Accuracy Retained

Calculate VRAMHugging FaceCompare

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Measured = run on this site · Estimated = not run here: calculated, or a figure this site has not verified · Community = public reports

FormatLevelBPWVRAMPPL LossSpeedSourceActions
GGUFQ4_K_M5.543.3 GB——Estimated
CalcHF
GGUFQ8_08.55.0 GB——Estimated
CalcHF

Similar models

Compare with Qwen3.5 9B
9B

Qwen3.5 9B

Alibaba Qwen3.5

Consumer GPUMac / Apple Silicon
6.6 GBmin VRAM—accuracy

The newest small Qwen and a common pick for 8 to 16 GB cards. Only 8 of its 32 layers keep a growing KV cache, so it can use a long context on modest hardware. At Q4_K_M it needs about 6.6 GB at 4K and 7.5 GB at 32K, comfortable on an 8 GB card. Its full 256K window needs about 15.2 GB. Q8_0 needs about 10.4 GB, comfortable from 12 GB up. Reasoning is off by default on the small Qwen3.5 sizes, and it reads images through a separate vision encoder. Sizes come from the published GGUF file sizes, and no per-level quality loss has been published.

2B

Qwen3.5 2B

Alibaba Qwen3.5

Consumer GPUMac / Apple Silicon
1.5 GBmin VRAM—accuracy

The 2B size of Qwen3.5, small enough for almost anything: old cards, base-model Macs, mini PCs and CPU-only servers. Only 6 of its 24 layers keep a growing KV cache, with 2 KV heads each. At Q4_K_M it needs about 1.5 GB at 4K context, 1.9 GB at 32K and 4.8 GB at its full 256K window. Even Q8_0 stays around 2.2 GB at 4K. Reasoning is off by default on the small Qwen3.5 sizes. Sizes come from the published GGUF file sizes, and no per-level quality loss has been published.

0.8B

Qwen3.5 0.8B

Alibaba Qwen3.5

Consumer GPUMac / Apple Silicon
0.6 GBmin VRAM—accuracy

The smallest Qwen3.5, for phones, single-board computers and as a fast draft or routing model next to a bigger one. At Q4_K_M it needs about 0.6 GB at 4K context and under 1 GB at 32K. Its full 256K window needs about 3.8 GB, almost all of it cache, so very long contexts cost more than the weights here. Sizes use the calculator's generic rates, since no GGUF file size could be checked, and no per-level quality loss has been published.

4B

Gemma 3 4B IT

Google Gemma 3

Consumer GPUMac / Apple Silicon
3.0 GBmin VRAM99.8%accuracy

Google Gemma 3 multimodal 4B. 128K context; strong vision + text on 8GB cards.

Running Qwen3.5 4B locally

At Q4_K_M and 4K of context, Qwen3.5 4B needs about 3.3 GB — 2.9 GB of weights, 0.13 GB of KV cache and a 0.3 GB activation buffer. The smallest cards in this index that clear that comfortably are 8 GB ones — 11 of them, from the Mac M1 8G up — and 78 of the 78 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.

What longer context costs

Going from 4K to 32K adds about 0.87 GB, taking the total to 4.3 GB. That is gentler than the parameter count suggests: only 8 of 32 layers keep a KV cache that grows with context, so the cache scales at a fraction of the usual rate. The model's native window is 256K; holding all of it at Q4_K_M would need about 12 GB.

Which build to download

This index only tracks Qwen3.5 4B in GGUF, across 2 levels (Q4_K_M, Q8_0). No per-level perplexity sweep has been published for this model, so the quality column is empty rather than estimated — within one model, more bits per weight is the only ordering the data supports. No throughput has been measured for this model on this site's hardware. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 — CUDA only, and now archived, so local use rather than serving.

Common questions

How much VRAM does Qwen3.5 4B need?
About 3.3 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 4.3 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.
Will Qwen3.5 4B run on a 8GB GPU?
Yes — at Q4_K_M and 4K context it needs about 3.3 GB, which leaves 2.7 GB spare on a Mac M1 8G, or on any of the other 8 GB cards here (11 in all). That is the smallest size in this index that clears it comfortably; 78 of 78 do.
Which quantization of Qwen3.5 4B should I use?
No published quality comparison exists for this model, so pick by footprint: Q4_K_M is the level most people run, and a higher bits-per-weight level is more faithful. All 2 levels in the index are Q4_K_M, Q8_0.

Where this model fits

Sized at Q4_K_M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory.

Runs comfortably on
Mac M1 8G8GB · +2.7Mac M3 8G8GB · +2.7RTX 40608GB · +4.7RTX 4060 Ti 8G8GB · +4.7Radeon RX 9060 XT 8G8GB · +4.7
Ships in
GGUF
Try it yourself
Size it in the calculatorGenerate the run command

How to actually run this

Deployment guides for this model and this class of hardware.

This page's figures change when the model or the runtime does.Last updated 2026-10-11 RSS → /feed.xml