Run Nanbeige4.3-33B on M3 Ultra

The LLMCheck index estimates Nanbeige4.3-33B at ~35 tok/s on an M3 Ultra at Q4_K_M, scaled from its community-measured oQ6e run on this chip with the published bandwidth model, not a measured Q4_K_M run. It needs about 17 GB of unified memory. It is Nanbeige's 33.1B dense model, released under the Apache 2.0 licence.

Speed
estimated~35
tok/s
First Token
—
seconds
RAM Needed
17
GB minimum
Engine
—
estimate
Want to run Nanbeige4.3-33B faster — or step up to bigger models? Find your Mac →

The figure

This is an LLMCheck index estimate from its published two-term bandwidth model, not a measured run; the index labels it so everywhere it appears. The bandwidth formula’s typical error for dense models is ±9%, against 75 measured runs of 20 models (how it is computed). Own this Mac? Submit a real run →

MetricValue
Tokens per secondestimated~35 tok/s
Provenanceestimate · how estimates are made
QuantizationQ4_K_M
Minimum RAM17 GB
Parameters33.1B
Chip bandwidth819 GB/s

Every figure for Nanbeige4.3-33B on the M3 Ultra

Each row as the index holds it, with its source. “Mac RAM” is the memory of the Mac a run used, not the model’s requirement (17 GB). The headline figure follows the reference rule: the lower-median measured plain-decode run at 5 bits or fewer (a run whose quant was not stated counts only when no stated-quant run qualifies), else the estimate; a run marked “not used to anchor estimates” is listed here but never becomes the headline.

SpeedQuantEngineMac RAMContextSourceNote
community25.6 tok/soQ6eMLX256 GB1komlx.ai80-core GPU. oMLX v0.7.3, MTP/DFlash off; Nanbeige4.3-33B-oQ6e; 26.6 GB peak. 24.9 tok/s at 4k.
community23.6 tok/soQ6eMLX96 GB1komlx.ai60-core GPU (819 GB/s, the same as the 80-core part). oMLX v0.7.3, MTP/DFlash off; Nanbeige4.3-33B-oQ6e; 26.6 GB peak. 23.4 tok/s at 4k, 19.0 at 32k.
community20.1 tok/soQ8eMLX256 GB1komlx.ai80-core GPU. oMLX v0.7.3, MTP/DFlash off; Nanbeige4.3-33B-oQ8e; 33.6 GB peak. 19.7 tok/s at 4k.
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

Speed by context depth: Nanbeige4.3-33B on the M3 Ultra

Measured figures only, each from its source’s own session; the index does not estimate long-context or prefill speed, so a missing cell is —. Each @ column is plain decode with that many tokens already in the prompt, from the same session as the row’s short-context figure: decode slows as the KV cache it reads grows. Prefill is prompt processing, the tokens per second a runtime reads a prompt at; with long agent contexts it sets how long you wait before the first token.

RunDecode (row)@4K@16K@32KPrefillTTFT
MLX · oQ6e · 256 GB Mac · omlx.aicommunity25.6 tok/s
1k
community24.9 tok/s——community355 tok/s
at 4K
community2.864 s
MLX · oQ6e · 96 GB Mac · omlx.aicommunity23.6 tok/s
1k
community23.4 tok/scommunity21 tok/scommunity19 tok/scommunity266 tok/s
at 4K
community3.827 s
MLX · oQ8e · 256 GB Mac · omlx.aicommunity20.1 tok/s
1k
community19.7 tok/s——community362 tok/s
at 4K
community2.84 s

Setup: run Nanbeige4.3-33B on a Mac

Ollama — the index has not verified an Ollama tag for Nanbeige4.3-33B, so it doesn’t print one (a guessed tag fails with “pull model manifest: file does not exist”). Search the Ollama library →

MLX — pick a build from Hugging Face’s MLX listings, then run it with its repo id:

pip install -U mlx-lm
mlx_lm.generate --model <repo-id> --prompt "Hello"

Downloads: Hugging Face repo → · Hugging Face model card →

Prefer a GUI? LM Studio downloads GGUF and MLX builds in one click. Step by step: install Ollama on a Mac.

Nanbeige4.3-33B on other Apple Silicon chips

ChipSpeedQuantEngineBandwidth
M5 Maxcommunity25 tok/soQ4eMLX614 GB/s
M4 Maxcommunity25 tok/s4-bitMLX546 GB/s
M1 Maxcommunity15 tok/soQ4eMLX400 GB/s

About Nanbeige4.3-33B

Nanbeige's Apache 2.0 dense 33.1B model (24 Oct 2026), 512K context. Artificial Analysis ranks it level with Qwen3.8-27B at the top of its small open models. Vendor-run card: Terminal-Bench 2.1 80.9, SWE-Bench Pro 60.3 (mini-swe-agent, not Scale SEAL), GPQA Diamond 89.5. IQ3_XXS is 14.5 GB and Q4_K_M 20.8 GB, so it targets 24 GB Macs; stock llama.cpp runs it (Llama architecture), and community oMLX runs measured ~25–27 tok/s on an M5 Max at 4-bit.

Apache 2.0 licence · 33.1B · 512K context · LLMCheck capability 46/50 · see its leaderboard rank →

Memory by context length

Estimated, not measured: the index’s minimum for Nanbeige4.3-33B (17 GB — the weights at the quant that fits, plus ~2 GB) plus the KV cache for that many tokens, computed from its config.json. GQA on all 52 layers (8 kv heads x 128). A 16-bit KV cache is the default in llama.cpp, Ollama, LM Studio and mlx-lm; a q8 cache halves the KV part. Coding agents hold 64K tokens or more. Runtimes also add a buffer that grows with context, so leave a few GB spare. macOS lets the GPU use only part of a Mac’s memory by default (figures for an M3 Ultra Mac on macOS 15, the lower default; macOS 26 allows more): “fits” means within the GPU memory a Mac of that tier can use with the limit raised, a tier tagged raise GPU limit fits only after sudo sysctl iogpu.wired_limit_mb raises it (the tooltip has the exact command), and the last column is the smallest Mac memory size whose default limit holds it (the GPU memory limit).

ContextKV cache (16-bit)RAM neededRAM, q8 KVSmallest tier that fitsWithin the default GPU limit
8K~1.7 GB~17.9 GB~17.4 GB24 GB Mac raise GPU limit32 GB Mac
32K~7.0 GB~23.1 GB~20.1 GB32 GB Mac raise GPU limit (macOS 15)36 GB Mac
64K (coding-agent context)~14.0 GB~30.1 GB~23.5 GB64 GB Mac48 GB Mac
128K~27.9 GB~44.0 GB~30.5 GB64 GB Macsame

System requirements

Macs with the M3 Ultra

🛒 Get a Mac that runs Nanbeige4.3-33B

Nanbeige4.3-33B needs about 17 GB of unified memory. These Apple Silicon Macs have enough to run it. Apple builds the higher-memory configurations to order; Amazon does not stock them.

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.

Compare More Models

See how Nanbeige4.3-33B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard