Qwen3-VL 30B-A3B Instruct
30B-A3BAlibaba Qwen3-VL
Multimodal MoE with only ~3B active parameters, so it stays responsive on Apple unified memory and survives CPU offload far better than a dense 30B. At Q4_K_M it needs about 19.9 GB at 4K, comfortable on a 24 GB card; Q3_K_M brings that to 15.1 GB. The vision encoder is a separate 1.1 GB file.
262K
Max Context
4
Quant Variants
GGUF Q8_0
Best Quality
+0.3%
Perplexity rise (best build)
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
| Format | Level | BPW | VRAM | PPL Loss | Speed | Source | Actions |
|---|---|---|---|---|---|---|---|
| GGUF | Q4_K_M | 4.88 | 19.9 GB | 2.6% | 95 tok/s | Community | |
| GGUF | Q3_K_M | 3.69 | 15.1 GB | 5.4% | 104 tok/s | Estimated | |
| GGUF | Q8_0 | 8.51 | 34.4 GB | 0.3% | — | Estimated | |
| AWQ | INT4 | 4 | 16.4 GB | 3.7% | 112 tok/s | Estimated |
Which file each size is for
A file size is not a memory figure: the VRAM column is the calculator's total at 4K context — weights plus KV cache plus a 10% activation buffer. Units differ on purpose: file sizes are decimal GB, as Hugging Face lists them; the VRAM column is GiB (1024³ bytes) with 2% added to the weights, so 7.12 GB of file counts as about 6.8 GiB there. A vision projector (mmproj), where the repo ships one, is a separate download and is in neither number.
- GGUF Q4_K_Mbartowski/Qwen_Qwen3-VL-30B-A3B-Instruct-GGUF · Qwen_Qwen3-VL-30B-A3B-Instruct-Q4_K_M.gguf · 18.63 GB (18,632,185,056 bytes) · + vision projector 1.08 GB, separate · listing read 2026-11-03
- GGUF Q3_K_Mbartowski/Qwen_Qwen3-VL-30B-A3B-Instruct-GGUF · Qwen_Qwen3-VL-30B-A3B-Instruct-Q3_K_M.gguf · 14.08 GB (14,076,804,320 bytes) · + vision projector 1.08 GB, separate · listing read 2026-11-03
- GGUF Q8_0bartowski/Qwen_Qwen3-VL-30B-A3B-Instruct-GGUF · Qwen_Qwen3-VL-30B-A3B-Instruct-Q8_0.gguf · 32.48 GB (32,483,933,408 bytes) · + vision projector 1.08 GB, separate · listing read 2026-11-03
- AWQ INT4Sized at the calculator's generic rate for this level; no file was checked.
Related community runs
These runs describe their own settings. Their speeds do not replace this estimate or prove your configuration fits.
Our reviewed link index has no run for this model yet. You can browse community reports or share your own test below.
Browse more runs on llamaPerf ↗Similar models
Compare with Qwen3-VL 8BQwen3-VL 8B Instruct
Alibaba Qwen3-VL
Current-generation vision-language model that still fits a single 8–12GB card at Q4 (~5.9GB). The realistic multimodal option for people without a 24GB GPU — note the vision encoder adds VRAM the KV-cache math below does not model.
Gemma 4 26B-A4B IT
Google Gemma 4
Google's Gemma 4 mixture-of-experts model: about 25B parameters in the text model, roughly 4B active per token, a 256K window and image input. Only 5 of its 30 layers keep a cache that grows with context, and those use fewer, wider heads, so the cache stays small — about 0.9 GB at 32K and 5.3 GB at the full 256K. At Q4_K_M that is about 18.8 GB at 32K: comfortable on a 24 GB card, which can still load the whole window (tight, about 23.6 GB). A 16 GB card cannot hold it, since the Q4_K_M file alone is 17.0 GB. The vision encoder is a separate 1.2 GB file on top. Sizes come from bartowski's GGUF files, whose Q4_K_M works out at 5.40 bits per weight, well above the generic 4-bit rate; Unsloth's UD-Q4_K_M is a different file, 0.09 GB smaller. No per-level quality loss has been published.
Gemma 4 31B IT
Google Gemma 4
Google's dense Gemma 4 flagship: about 31B parameters, a 256K window and image input. Only 10 of its 60 layers cache the full context, and those use four wide KV heads, so 128K of context adds about 11 GB of cache where a conventional 60-layer design would need about 120 GB. At Q4_K_M it needs about 22.1 GB at 4K, tight on a 24 GB card; Q3_K_M is about 18.3 GB at 4K. A 32 GB card holds Q4_K_M at 32K comfortably. Google also publishes its own quantization-aware (QAT) Q4_0 build, a single 17.7 GB file: about 20.1 GB at 4K, comfortable on 24 GB up to 16K. Its 1.2 GB vision encoder is a separate file, and with it loaded even 4K is tight on 24 GB. The other levels are sized from bartowski's GGUF files, and no per-level quality loss has been published. That repository also carries two MTP draft-head files (349 MB at Q4_0, 515 MB at Q8_0) for speculative decoding; they are not the model itself and are not counted in these sizes.
Qwen3.6 35B-A3B
Alibaba Qwen3.6
One of the most recommended models for a 24 GB card this year: 35.5B parameters, about 3B active per token, so it reads per token about as much as a 3B model. Only 10 of its 40 layers keep a growing KV cache, so context is cheap: at Q4_K_M it needs about 23.4 GB at 4K and 24.0 GB at 32K. On this site's rule that is tight on a 24 GB card, not comfortable, because it counts a working buffer most guides leave out. A 32 GB card, or a 48 GB Mac through the GPU's share of unified memory, has real room. It reads images through a separate vision encoder. Sizes come from bartowski's GGUF files; Unsloth's UD-Q4_K_M is a different file, 0.15 GB smaller. No per-level quality loss has been published.
Running Qwen3-VL 30B-A3B Instruct locally
At Q4_K_M and 4K of context, Qwen3-VL 30B-A3B Instruct needs about 19.9 GB — 17.7 GB of weights, 0.38 GB of KV cache and a 1.8 GB activation buffer. The smallest cards in this index that clear that comfortably are 24 GB ones — 5 of them, from the RTX 3090 up — and 32 of the 105 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 2.62 GB, taking the total to 22.8 GB. Weights do not move with context — only the KV cache does, and it grows linearly, so this is the number to watch when planning for long documents. The model's native window is 256K; holding all of it at Q4_K_M would need about 46 GB.
Which build to download
This index tracks 2 formats for it — GGUF, AWQ — across 4 levels. Q8_0 carries the lowest published perplexity loss at 0.3%. The fastest level listed is AWQ INT4 at about 112 tok/s on an RTX 4090, batch 1 — an estimate, not a run 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-VL 30B-A3B Instruct need?
- About 19.9 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 22.8 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-VL 30B-A3B Instruct run on a 24GB GPU?
- Yes — at Q4_K_M and 4K context it needs about 19.9 GB, which leaves 4.1 GB spare on a RTX 3090, or on any of the other 24 GB cards here (5 in all). That is the smallest size in this index that clears it comfortably; 32 of 105 do.
- Which quantization of Qwen3-VL 30B-A3B Instruct should I use?
- Q8_0 has the lowest published quality loss (0.3%), and Q4_K_M is the level most people run. All 4 levels in the index are Q4_K_M, Q3_K_M, Q8_0, AWQ INT4. Note this is a mixture-of-experts model — all parameters must be resident even though only a fraction are active per token, so the memory cost follows the total, not the active count.
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
- RTX 309024GB · +4.1Radeon RX 7900 XTX24GB · +4.1RTX 409024GB · +4.1RTX 5090 Laptop GPU24GB · +4.1Tesla P40 24G24GB · +4.1
- Tight but possible
- Radeon RX 7900 XT20GB
- Compared here
- GGUF vs AWQ
- Try it yourself
- Size it in the calculatorGenerate the run command
Cards for this model
- RTX 5090
- RTX 5080
- RTX 5070 Ti
- RTX 5060 Ti 16G
- RTX 4090
- RTX 4080 Super
- RTX 4070 Ti Super
- RTX 4060 Ti 16G
- RTX 3090
- A100 80G
- A100 40G
- L40S 48G
- A40 48G
- H100 80G
- DGX Spark 128G
- DGX Spark 64G
- Tesla P100 16G
- Tesla P40 24G
- Mac M5 Max 128G
- Mac M5 Pro 64G
- Mac M5 32G
- Mac M4 Max 128G
- Mac M4 Max 36G
- Mac M4 Pro 48G
- Mac M4 Pro 24G
- Mac M3 Max 128G
- Mac M3 Max 48G
- Mac M3 Pro 36G
- Mac M4 24G
- Mac M1 Max 64G
- Mac M2 Max 96G
- Radeon RX 9070 XT
- Radeon RX 9070
- Radeon RX 9060 XT 16G
- Radeon RX 7900 XTX
- Radeon RX 7900 XT
- Radeon RX 7900 GRE
- Radeon RX 7800 XT
- Radeon RX 7600 XT
- Radeon RX 6900 XT
- Radeon RX 6800 XT
- Radeon PRO W7900 48G
- Radeon AI PRO R9700 32G
- Instinct MI100 32G
- Arc A770 16G
- Arc Pro B70 32G
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 2026-11-22 RSS → /feed.xml