localLLMrig
Menu

Which GPUs and Macs run Nanbeige4.3-33B?

Key facts

Nanbeige4.3-33B needs about 23 GB of graphics memory. It runs on 6 of the 10 graphics card setups on this page, such as the RTX 3090.

About 23.3 GB at Q4_K_M, our estimate. Checked . bartowski Q4_K_M GGUF.

The cheapest graphics card on our list that runs it (it still needs the rest of a PC): GeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings).

Fast~32 tok/sAnswers appear faster than you can read them.

Our price is for a used card. These shops mostly sell new ones, so their price can be higher.

EU shops · Shown to visitors in Europe.

US shops · Shown to visitors outside Europe.

If you buy through these links we may earn a commission. It doesn't change our ranking. How shop links work

As an Amazon Associate I earn from qualifying purchases.

Als Amazon-Partner verdiene ich an qualifizierten Verkäufen.

Als Amazon-Partner verdien ik aan in aanmerking komende aankopen.

We never pass off an estimate as a benchmark. Commissions never change which hardware we recommend. How we calculate

A complete machine that runs it: Mac Studio M4 Max 36GB, about $2,116€1,890 (used). Comfortable~8.7 tok/s

Find hardware for Nanbeige4.3-33BAbout this model

LIVE IN BROWSER · $0 · NO LOGIN

Test 10 open LLMs free in your browser before downloading 21 GB for Nanbeige4.3-33B

Open full 8-model playground ↗

Before downloading 20.79 GB of Q4_K_M weights for Nanbeige4.3-33B (33.12B dense parameters, 524,288 max context, Apache-2.0; author-reported Terminal-Bench 80.9 and DeepSWE 65.5, not independently verified on this site), you can test 10 open LLMs free in your browser at https://localllmrig.com/ with no login and 0 GB of local VRAM. The prompts below run Recursive Flint and Gemma 4 31B. Nanbeige4.3-33B itself is not one of the free models, so trying it in the chat needs a pass once a provider lists it.

Test 10 open LLMs free in your browser →https://localllmrig.com/can-i-run/nanbeige-4-3-33b

Click a starter prompt below or type your own question to watch Recursive Flint stream side by side against Gemma 4 31B right on this page:

Get a 1-line alert when a faster quant for Nanbeige4.3-33B drops — or when GPUs that run it drop >10%

Get a 1-line alert when a new open-weight model fits 24 GB VRAM (23.3 GB at Q4 for Nanbeige4.3-33B) or when used RTX 3090 / 4090 & Mac Studio prices drop >10% — weekly, zero spam.

Which graphics cards run it

Seven popular graphics cards and two PCs with two cards each, at the standard quality (Q4). Click one for the full answer: memory, speed and price.

Runs well6

The whole model fits in the graphics memory.

Doesn't fit4

Not enough graphics memory: it needs about 23.3 GB. In a PC with enough normal memory it runs slowly: Budget PC with RTX 3060 12GB, about $1,310€1,361 (with a used graphics card). Very slow~1.8 tok/s

Every model on every card

Which Macs and mini PCs run it

Macs and mini PCs from the picker, at the standard quality (Q4). A Mac shares its memory with the rest of the computer. Each name opens that machine's page.

Runs well8

The whole model fits in the memory the graphics can use.

Runs slowly2

The whole model fits, but it answers slower than you read.

Doesn't fit2

Not enough shared memory: it needs about 23.3 GB.

Cheapest hardware for each size

From all 43 graphics cards, PCs and Macs on our list. "Runs slowly" means part of the model runs from normal memory: cheaper, but much slower. A smaller download needs less memory and answers a little less well.

Prices excl. shipping unless marked. Euro prices incl. VAT where the seller charges it. Dollar prices are converted from our euro prices without the 21% EU VAT, before US sales tax.

Prices moved: see Building a local LLM rig in the RAMageddon.

About Nanbeige4.3-33B

33.12B parameters. Parameter count is an estimate. More parameters usually means a smarter model that needs more memory.

Licence:
Apache-2.0 source
Longest conversation:
about 786 pages of text (524,288 tokens)
Input:
text
Released:
source
Sources and method

Dense coder and reasoning model, 33.12B parameters, Apache-2.0 on the model-card metadata (the repo had no LICENSE file on 26 Oct 2026). Config: 52 layers, 8 KV heads, head dim 128, context 524,288. The parameter formula is about 19.9 GB at Q4, 35.4 GB at Q8 and 66.2 GB at FP16. Bartowski's GGUF listing on 26 Oct 2026 measured Q4_K_M at 20.79 GB, Q8_0 at 35.20 GB and the two BF16 shards at 66.24 GB together. IQ2_M on the same listing measured 12.19 GB on 27 Oct 2026 (12,187,167,872 bytes). At 8,192 tokens our estimate adds about 1.74 GB of conversation memory and 0.80 GB of working space, so the Q4_K_M total is about 23.3 GB. That fits a 24 GB GPU (an RTX 3090 or RTX 4090 leaves about 23.4 GB usable). A 32 GB Mac leaves about 21.3 GB for the GPU, so the same Q4 total is over that default share; IQ4_XS at 18.64 GB is the file that lands inside it. The IQ2_M total is about 14.7 GB, which fits a 16 GB card and misses a 12 GB card. Q8_0 at 35.20 GB fits 48 GB of VRAM or 64 GB of unified memory. FP16 at 66.24 GB fits 96 GB or 128 GB of unified memory, or two 48 GB GPUs. The Terminal-Bench 80.9 and DeepSWE 65.5 figures are the author's, and are not yet independently verified.

Author-reported on the Nanbeige model card, not an independent measurement on this site. Terminal-Bench 2.1: 80.9. DeepSWE: 65.5. The same card puts both above Qwen3.8-27B. A 3B sibling, Nanbeige4.3-3B, is named as a later distillation and is not a row here. Source: https://huggingface.co/Nanbeige/Nanbeige4.3-33B

Builder interview

Xijing (Thomas) Wang is testing Nanbeige4.3-33B on a MacBook Pro M5 Max with 128 GB unified memory (about 107 GB of that is GPU-usable), alongside his daily Qwen3.8-27B at 5-bit on oMLX. Self-reported, 26 October 2026. Read Xijing (Thomas) Wang's interview.

Ran Nanbeige4.3-33B on your own hardware? Send us your llama-bench result.

Parameter source · Architecture source · Model page

Memory at each quality level

Each download of Nanbeige4.3-33B is a different size. The total adds the file, the memory a conversation of about 12 pages of text (8,192 tokens) takes, and 0.8 GB of working space. A measured file size is labelled; the rest is our estimate. The last column is the cheapest machine that holds the total.

Swipe the table sideways to see every column, up to the cheapest machine.

Memory per quant for Nanbeige4.3-33B
Quality (file)File sizeConversationWorking spaceTotalCheapest machine that holds it
BF1666.24 GBmeasured GGUF1.7 GB0.8 GB68.8 GBMac Studio M4 Max 128GB, $3,683€3,290 (used), price unverified
Q8_035.20 GBmeasured GGUF1.7 GB0.8 GB37.7 GBMac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified
Q6_K29.02 GBmeasured GGUF1.7 GB0.8 GB31.6 GBMac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified
Q5_K_M25.07 GBmeasured GGUF1.7 GB0.8 GB27.6 GBMac mini M4 Pro 64GB, $2,116€1,890 (used), price unverified
Q4_K_M20.79 GBmeasured GGUF1.7 GB0.8 GB23.3 GBGeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings)
IQ4_XS18.64 GBmeasured GGUF1.7 GB0.8 GB21.2 GBGeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings)
Q3_K_M15.92 GBmeasured GGUF1.7 GB0.8 GB18.5 GBGeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings)
IQ3_XS15.21 GBmeasured GGUF1.7 GB0.8 GB17.8 GBGeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings)
IQ3_XXS14.49 GBmeasured GGUF1.7 GB0.8 GB17.0 GBGeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings)
Q2_K13.53 GBmeasured GGUF1.7 GB0.8 GB16.1 GBGeForce RTX 3090 24GB, $1,395€1,246, used (median of sold listings)
IQ2_M12.19 GBmeasured GGUF1.7 GB0.8 GB14.7 GBRadeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list)
IQ2_XXS10.07 GBmeasured GGUF1.7 GB0.8 GB12.6 GBRadeon RX 9060 XT 16GB, $522€564, new (cheapest in-stock board on GPU PRIX's German board list)

Speeds and memory are our estimate from the hardware specs, not a measured test. Prices are dated and may change. How we calculate

Questions

Can I run Nanbeige4.3-33B on an RTX 3090 or RTX 4090 (24 GB VRAM)?
Yes, by our estimate, and it is a tight fit. At 8,192 tokens, 20.79 GB measured GGUF + 1.74 GB conversation memory at 8,192 tokens + 0.80 GB working space = 23.33 GB / 23.3 GB total estimate (52 layers, 8 KV heads, head dim 128). A 24 GB card leaves 23.4 GB usable, so Q4_K_M fits with about 0.07 GB to spare. 6 of the 10 GPU setups on https://localllmrig.com/can-i-run/nanbeige-4-3-33b hold the standard file: GeForce RTX 3090 24GB (€1,246 / $1,395, about 32 tok/s, our estimate); GeForce RTX 4090 24GB (€2,185 / $2,446, about 35 tok/s, our estimate); GeForce RTX 5090 32GB (€7,367 / $6,816, about 61 tok/s, our estimate); Radeon RX 7900 XTX 24GB (€1,254 / $1,404, about 32 tok/s, our estimate); Dual RTX 3090, 128 GB RAM (€5,452 / $5,528, price unverified, about 35 tok/s, our estimate); Dual RTX 4090, 128 GB RAM (€7,330 / $7,631, price unverified, about 38 tok/s, our estimate). GeForce RTX 3090 24GB, GeForce RTX 4090 24GB, and Radeon RX 7900 XTX 24GB each leave that 23.4 GB usable. For a longer conversation on one 24 GB card, IQ4_XS (18.64 GB measured GGUF, 21.2 GB total estimate) frees 2.15 GB, or quantize the conversation memory (-ctk q8_0 -ctv q8_0). Q5_K_M (25.07 GB measured GGUF, 27.6 GB total estimate) is 4.2 GB over a 24 GB card and needs a 32 GB GPU (GeForce RTX 5090 32GB, 31.4 GB usable, about 61 tok/s, our estimate), two 24 GB cards, or a 64 GB Mac or Ryzen AI Max+ 395 mini PC.
Can a 16 GB or 12 GB GPU (RTX 4060 Ti 16GB, RTX 5080 16GB, or RTX 3060 12GB) run Nanbeige4.3-33B?
Not at standard 4-bit quality (Q4_K_M, 23.3 GB total estimate) or IQ4_XS (21.2 GB total estimate). A 16 GB card (GeForce RTX 4060 Ti 16GB at €899 / $832, or GeForce RTX 5080 16GB) leaves 15.4 GB usable by our estimate. Q3_K_M (15.92 GB measured GGUF, 18.5 GB total estimate), IQ3_XS (15.21 GB measured GGUF, 17.8 GB total estimate), IQ3_XXS (14.49 GB measured GGUF, 17.0 GB total estimate) all exceed 15.4 GB at 8,192 tokens. To fit entirely inside a 16 GB card, step down to IQ2_M (12.19 GB measured GGUF, 14.7 GB total estimate) or IQ2_XXS (10.07 GB measured GGUF, 12.6 GB total estimate), which trades away coding and reasoning accuracy. GeForce RTX 3060 12GB leaves 11.4 GB usable (€261 / $292) and cannot hold IQ2_XXS. Budget PC with RTX 3060 12GB runs Q4_K_M by spilling into normal memory at about 1.8 tok/s, our estimate. Qwen3.8-27B (https://localllmrig.com/can-i-run/qwen3.8-27b) at UD-IQ3_XXS (10.93 GB measured GGUF, 12.3 GB total estimate) or Gemma 4 26B A4B (https://localllmrig.com/can-i-run/gemma-4-26b-a4b) at UD-IQ4_XS (13.6 GB measured GGUF, 14.8 GB total estimate).
Which Mac or Ryzen AI Max+ 395 mini PC runs Nanbeige4.3-33B best, and why is a 32 GB Mac tight at Q4_K_M?
Mac mini M6 32GB leaves 21.3 GB usable of 32 GB (€1,530 / $1,416, price unverified), 2.0 GB short of the 23.3 GB Q4_K_M total estimate at 8,192 tokens. IQ4_XS (18.64 GB measured GGUF, 21.2 GB total estimate) is the file that fits a 32 GB Mac. Q4_K_M (20.79 GB measured GGUF, 23.3 GB total estimate) does not. Mac Studio M4 Max 36GB (27.0 GB usable, €1,890 / $2,116, price unverified, about 8.7 tok/s, our estimate) and Mac Studio M5 Max 36GB (27.0 GB usable, €3,029 / $2,802, about 9.8 tok/s, our estimate) hold Q4_K_M at 23.3 GB. GMKtec EVO-X2 (Ryzen AI Max+ 395) 64GB leaves 48.0 GB for graphics (€2,199 / $2,035) and holds Q4_K_M (23.3 GB, about 9.1 tok/s, our estimate). Mac Studio M5 Max 128GB leaves 96.0 GB usable (about 13.0 tok/s, our estimate). Mac Studio M5 Ultra 96GB leaves 72.0 GB usable and Mac Studio M5 Ultra 256GB leaves 192.0 GB usable (about 25 tok/s, our estimate). Q5_K_M (27.6 GB total), Q6_K (31.6 GB total), Q8_0 (37.7 GB total) fit 64 GB unified memory (48.0 GB usable). BF16 (66.24 GB measured GGUF, 68.8 GB total estimate) fits 96 GB or 128 GB unified memory. A 128 GB M5 Max write-up is at https://localllmrig.com/interviews/thomas-wang-m5-max-128gb-omlx. Ryzen AI Max+ 395 is the chip in GMKtec EVO-X2 (Ryzen AI Max+ 395) 64GB.
Nanbeige4.3-33B vs Qwen3.8-27B: how do their VRAM requirements and 24 GB GPU fit compare?
Both are dense Apache-2.0 models that fit a single 24 GB GPU (23.4 GB usable), but Qwen3.8-27B needs 5.53 GB less VRAM at standard 4-bit quality and 3.25× less conversation memory per token, by our estimate. Nanbeige4.3-33B is 33.12B parameters with 52 full-attention layers, 23.33 GB / 23.3 GB at Q4_K_M (20.79 GB measured GGUF + 1.74 GB conversation memory + 0.80 GB working space), leaving 0.07 GB on a 24 GB card (about 32 tok/s, our estimate on an RTX 3090, about 35 tok/s, our estimate on an RTX 4090). Qwen3.8-27B is 27.78B parameters with 48 linear-attention layers and 16 full-attention layers, 17.80 GB at UD-Q4_K_M (0.54 GB versus 1.74 GB of conversation memory at 8,192 tokens). UD-Q5_K_XL is 22.2 GB total. UD-Q6_K is 23.3 GB total. At 32,768 tokens, Qwen3.8-27B UD-Q4_K_M is 19.41 GB and Nanbeige4.3-33B is 28.57 GB. Qwen3.8-27B is at https://localllmrig.com/can-i-run/qwen3.8-27b.
Where can I test open coding and reasoning LLMs free in my browser before downloading 20.79 GB for Nanbeige4.3-33B?
Nanbeige4.3-33B is not one of the 10 free models. Before downloading 20.79 GB of Q4_K_M weights you can test 10 open-weight models side by side for free in your browser at https://localllmrig.com/ or from https://localllmrig.com/can-i-run/nanbeige-4-3-33b, with no login and 0 GB of local VRAM. Compare Recursive Flint (39.79B total, 2.5B active, https://localllmrig.com/can-i-run/flint), Gemma 4 31B (31.27B dense, https://localllmrig.com/can-i-run/gemma-4-31b), and Gemma 4 26B A4B (https://localllmrig.com/can-i-run/gemma-4-26b-a4b) on your own coding and reasoning prompts (5 free questions every 10 minutes). Trying Nanbeige4.3-33B itself in the chat needs a pass once a provider lists it.
What licence does Nanbeige4.3-33B use, and how do I run it locally with llama.cpp, Ollama, or vLLM on 24 GB?
The Nanbeige/Nanbeige4.3-33B model-card metadata lists Apache-2.0 (the repository had no standalone LICENSE file on 26 Oct 2026; our reading of the licence, not legal advice). It uses standard LlamaForCausalLM (52 layers, 8 KV heads, head dim 128, 524,288 max context) and runs in current llama.cpp, Ollama, vLLM, SGLang, and oMLX builds. On a 24 GB GPU (GeForce RTX 3090 24GB, GeForce RTX 4090 24GB, or Radeon RX 7900 XTX 24GB), run Nanbeige_Nanbeige4.3-33B-Q4_K_M.gguf (20.79 GB) in llama.cpp with -ngl 99 -fa -c 8192, or add -ctk q8_0 -ctv q8_0 (or use IQ4_XS at 18.64 GB) for a longer context. File sizes are on https://localllmrig.com/can-i-run/nanbeige-4-3-33b.
Can I run Nanbeige4.3-33B on 24GB?
Yes, by our estimate. Nanbeige4.3-33B needs about 23.3 GB at the standard quality, and a 24 GB card leaves about 23.4 GB usable.
Can I run Nanbeige4.3-33B on a 128GB Mac?
Yes, by our estimate. Nanbeige4.3-33B fits on Mac Studio M4 Max 128GB and Mac Studio M5 Max 128GB. Each leaves about 96.0 GB usable of its 128 GB.
How fast is Nanbeige4.3-33B on an RTX 5090?
Fast: about 61 tokens per second (tok/s), our estimate. Answers appear faster than you can read them.