Nanbeige4.3 33B hardware requirements
About the model
- Parameters
- 33.12B
- Attention
- Full attention
- Max context
- 524,288 tokens
- Released
- 2026-10-24
- Model card
- Nanbeige4.3 33B on Hugging Face
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| Q2_K | 13.53 GB | Heavy loss | Community GGUF · bartowski |
| IQ4_XS | 18.64 GB | Good balance | Community GGUF · bartowski |
| Q4_K_Mbaseline | 20.79 GB | Good balance | Community GGUF · bartowski |
| Q8_0 | 35.20 GB | Near-lossless | Community GGUF · bartowski |
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k | 256k |
|---|---|---|---|---|---|---|---|
| Q2_K | 13.7 | 14.6 | 16.4 | 20.0 | 27.3 | 41.9 | 71.0 |
| IQ4_XS | 19.4 | 20.3 | 22.1 | 25.8 | 33.1 | 47.6 | 76.7 |
| Q4_K_M | 21.5 | 22.4 | 24.2 | 27.9 | 35.2 | 49.7 | 78.8 |
| Q8_0 | 35.3 | 36.2 | 38.1 | 41.7 | 49.0 | 63.5 | 92.7 |
Which GPUs can run Nanbeige4.3 33B?
How to read the verdicts
- Runs great
- Fully on the GPU at 20 tok/s or more
- Runs well
- Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
- Runs slowly
- 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
- Won't run
- Does not fit, or under 2 tok/s
Dense models split between GPU and CPU slow down sharply — the CPU side sets the pace. MoE models that keep only their experts in system RAM degrade far more gently.
Filter this list by budget, type and context in the calculator
Scroll sideways to see every column.
| Hardware | Verdict | Speed | Quant | Memory | Runs as | Context | Notes | Price |
|---|---|---|---|---|---|---|---|---|
| GeForce RTX 5090 | Runs great | est. 55.7 tok/s49.0–62.3calibrated estimate ±12% | Q4_K_M | 23.0 / 32.0 GB | Full GPU | up to 32k | — | $4,200 street (as of 2026-08-09) |
| NVIDIA RTX PRO 6000 Blackwell | Runs great | est. 55.7 tok/s49.0–62.3calibrated estimate ±12% | Q4_K_M | 23.0 / 96.0 GB | Full GPU | up to 64k | — | — |
| NVIDIA RTX PRO 6000 Blackwell Max-Q | Runs great | est. 55.7 tok/s49.0–62.3calibrated estimate ±12% | Q4_K_M | 23.0 / 96.0 GB | Full GPU | up to 64k | — | — |
| Radeon RX 7900 XTX | Runs great | est. 32.4 tok/s28.5–36.3calibrated estimate ±12% | Q4_K_M | 23.0 / 24.0 GB | Full GPU | up to 8k | — | $999 launch MSRP |
| GeForce RTX 3090 Ti | Runs great | est. 31.3 tok/s27.6–35.1calibrated estimate ±12% | Q4_K_M | 23.0 / 24.0 GB | Full GPU | up to 8k | — | $1,999 launch MSRP |
| GeForce RTX 4090 | Runs great | est. 31.3 tok/s27.6–35.1calibrated estimate ±12% | Q4_K_M | 23.0 / 24.0 GB | Full GPU | up to 8k | — | $2,755 street (as of 2026-08-09) |
| Apple M5 Ultra · 96 GB | Runs great | est. 31.1 tok/s24.8–37.3calibrated estimate ±20% | Q4_K_M | 23.1 / 67.2 GB | Unified memory | up to 8k | — | — |
| GeForce RTX 3090 | Runs well | est. 29.1 tok/s25.6–32.6calibrated estimate ±12% | Q4_K_M | 23.0 / 24.0 GB | Full GPU | up to 8k |
| $1,050 street (as of 2026-08-09) |
| GeForce RTX 5090 Laptop | Runs well | est. 27.8 tok/s24.5–31.2calibrated estimate ±12% | Q4_K_M | 23.0 / 24.0 GB | Full GPU | up to 8k |
| — |
| Apple M3 Ultra · 96 GB | Runs well | est. 20.7 tok/s16.6–24.9calibrated estimate ±20% | Q4_K_M | 23.1 / 67.2 GB | Unified memory | up to 64k |
| — |
| Apple M5 Max (40-core GPU) · 48 GB | Runs well | est. 20.7 tok/s16.6–24.8calibrated estimate ±20% | Q4_K_M | 23.1 / 33.6 GB | Unified memory | up to 32k |
| — |
| Apple M2 Ultra · 64 GB | Runs well | est. 20.2 tok/s16.2–24.3calibrated estimate ±20% | Q4_K_M | 23.1 / 44.8 GB | Unified memory | up to 64k | — | — |
| Apple M4 Max (40-core GPU) · 48 GB | Runs well | est. 18.4 tok/s14.7–22.1calibrated estimate ±20% | Q4_K_M | 23.1 / 33.6 GB | Unified memory | up to 32k | — | — |
| Apple M5 Max (32-core GPU) · 36 GB | Runs well | est. 15.5 tok/s12.4–18.6calibrated estimate ±20% | Q4_K_M | 23.1 / 25.2 GB | Unified memory | up to 16k | — | — |
| Apple M4 Max (32-core GPU) · 36 GB | Runs well | est. 13.8 tok/s11.1–16.6calibrated estimate ±20% | Q4_K_M | 23.1 / 25.2 GB | Unified memory | up to 16k | — | — |
| Apple M5 Pro · 48 GB | Runs slowly | est. 10.4 tok/s8.3–12.4calibrated estimate ±20% | Q4_K_M | 23.1 / 33.6 GB | Unified memory | up to 32k |
| — |
| NVIDIA DGX Spark · 128 GB | Runs slowly | est. 9.4 tok/s7.6–11.3calibrated estimate ±20% | Q4_K_M | 23.1 / 116.9 GB | Unified memory | up to 128k |
| $3,999 launch MSRP (128 GB) |
| Apple M4 Pro · 48 GB | Runs slowly | est. 9.2 tok/s7.4–11.0calibrated estimate ±20% | Q4_K_M | 23.1 / 33.6 GB | Unified memory | up to 32k |
| — |
| Radeon RX 7900 XT | Runs slowly | est. 8.3 tok/s6.7–10.0calibrated estimate ±20% | Q4_K_M | 20.0 / 20.0 GB + 3.7 GB RAM | Partial offload | up to 32k |
| $899 launch MSRP |
| Ryzen AI Max+ 395 (Strix Halo) · 32 GB | Runs slowly | est. 5.7 tok/s4.0–7.4theoretical estimate ±30% | Q4_K_M | 22.5 GB RAM | CPU only | up to 32k |
| $1,999 launch MSRP (128 GB) |
| GeForce RTX 5080 | Runs slowly | est. 4.8 tok/s3.9–5.8calibrated estimate ±20% | Q4_K_M | 16.0 / 16.0 GB + 7.7 GB RAM | Partial offload | up to 16k |
| $1,256 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti | Runs slowly | est. 4.8 tok/s3.8–5.7calibrated estimate ±20% | Q4_K_M | 16.0 / 16.0 GB + 7.7 GB RAM | Partial offload | up to 16k |
| $949 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Runs slowly | est. 4.8 tok/s3.8–5.7calibrated estimate ±20% | Q4_K_M | 16.0 / 16.0 GB + 7.7 GB RAM | Partial offload | up to 16k |
| — |
| GeForce RTX 4080 Super | Runs slowly | est. 4.7 tok/s3.7–5.6calibrated estimate ±20% | Q4_K_M | 16.0 / 16.0 GB + 7.7 GB RAM | Partial offload | up to 16k |
| $999 launch MSRP |
| GeForce RTX 4080 | Runs slowly | est. 4.7 tok/s3.7–5.6calibrated estimate ±20% | Q4_K_M | 16.0 / 16.0 GB + 7.7 GB RAM | Partial offload | up to 16k |
| $1,199 launch MSRP |
| Radeon RX 9070 | Runs slowly | est. 4.6 tok/s3.7–5.6calibrated estimate ±20% | Q4_K_M | 16.0 / 16.0 GB + 7.7 GB RAM | Partial offload | up to 16k |
| $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Runs slowly | est. 4.6 tok/s3.7–5.6calibrated estimate ±20% | Q4_K_M | 16.0 / 16.0 GB + 7.7 GB RAM | Partial offload | up to 16k |
| $689 street (as of 2026-08-09) |
| Radeon RX 7800 XT | Runs slowly | est. 4.6 tok/s3.7–5.5calibrated estimate ±20% | Q4_K_M | 16.0 / 16.0 GB + 7.7 GB RAM | Partial offload | up to 16k |
| $499 launch MSRP |
| GeForce RTX 4070 Ti Super | Runs slowly | est. 4.6 tok/s3.7–5.5calibrated estimate ±20% | Q4_K_M | 16.0 / 16.0 GB + 7.7 GB RAM | Partial offload | up to 16k |
| $799 launch MSRP |
| GeForce RTX 4090 Laptop | Runs slowly | est. 4.5 tok/s3.6–5.4calibrated estimate ±20% | Q4_K_M | 16.0 / 16.0 GB + 7.7 GB RAM | Partial offload | up to 16k |
| — |
| GeForce RTX 5060 Ti 16GB | Runs slowly | est. 4.3 tok/s3.5–5.2calibrated estimate ±20% | Q4_K_M | 16.0 / 16.0 GB + 7.7 GB RAM | Partial offload | up to 16k |
| $569 street (as of 2026-08-09) |
| Radeon RX 9060 XT 16GB | Runs slowly | est. 4.1 tok/s3.3–4.9calibrated estimate ±20% | Q4_K_M | 16.0 / 16.0 GB + 7.7 GB RAM | Partial offload | up to 16k |
| $449 street (as of 2026-08-09) |
| GeForce RTX 4060 Ti 16GB | Runs slowly | est. 3.9 tok/s3.1–4.7calibrated estimate ±20% | Q4_K_M | 16.0 / 16.0 GB + 7.7 GB RAM | Partial offload | up to 16k |
| $499 launch MSRP |
| Apple M6 · 32 GB | Runs slowly | est. 3.8 tok/s2.6–4.9theoretical estimate ±30% | Q4_K_M | 22.5 GB RAM | CPU only | up to 32k | — | — |
| Apple M5 · 32 GB | Runs slowly | est. 3.4 tok/s2.4–4.4theoretical estimate ±30% | Q4_K_M | 22.5 GB RAM | CPU only | up to 16k | — | — |
| GeForce RTX 3080 12GB | Runs slowly | est. 3.3 tok/s2.7–4.0calibrated estimate ±20% | Q4_K_M | 12.0 / 12.0 GB + 11.7 GB RAM | Partial offload | up to 8k | — | $799 launch MSRP |
| GeForce RTX 5070 | Runs slowly | est. 3.3 tok/s2.6–3.9calibrated estimate ±20% | Q4_K_M | 12.0 / 12.0 GB + 11.7 GB RAM | Partial offload | up to 8k | — | $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Runs slowly | est. 3.3 tok/s2.6–3.9calibrated estimate ±20% | Q4_K_M | 12.0 / 12.0 GB + 11.7 GB RAM | Partial offload | up to 8k | — | — |
| GeForce RTX 4070 | Runs slowly | est. 3.2 tok/s2.6–3.9calibrated estimate ±20% | Q4_K_M | 12.0 / 12.0 GB + 11.7 GB RAM | Partial offload | up to 8k | — | $599 launch MSRP |
| GeForce RTX 4070 Super | Runs slowly | est. 3.2 tok/s2.6–3.9calibrated estimate ±20% | Q4_K_M | 12.0 / 12.0 GB + 11.7 GB RAM | Partial offload | up to 8k | — | $599 launch MSRP |
| GeForce RTX 4080 Laptop | Runs slowly | est. 3.2 tok/s2.5–3.8calibrated estimate ±20% | Q4_K_M | 12.0 / 12.0 GB + 11.7 GB RAM | Partial offload | up to 8k | — | — |
| Intel Arc B580 | Runs slowly | est. 3.1 tok/s2.5–3.8calibrated estimate ±20% | Q4_K_M | 12.0 / 12.0 GB + 11.7 GB RAM | Partial offload | up to 8k | — | $290 street (as of 2026-08-09) |
| GeForce RTX 3060 12GB | Runs slowly | est. 3.1 tok/s2.5–3.7calibrated estimate ±20% | Q4_K_M | 12.0 / 12.0 GB + 11.7 GB RAM | Partial offload | up to 8k | — | $250 street (as of 2026-08-09) |
| GeForce RTX 2080 Ti | Runs slowly | est. 3.1 tok/s2.4–3.7calibrated estimate ±20% | Q4_K_M | 11.0 / 11.0 GB + 12.7 GB RAM | Partial offload | up to 8k | — | $999 launch MSRP |
| Apple M4 · 32 GB | Won't runTry IQ4_XS: Runs slowly | est. 4.5 tok/s3.6–5.4calibrated estimate ±20% | IQ4_XS | 21.0 / 22.4 GB | Unified memory | up to 8k | — | — |
| GeForce RTX 3070 | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 4.3 tok/s3.5–5.2calibrated estimate ±20% | Q2_K | 8.0 / 8.0 GB + 8.4 GB RAM | Partial offload | up to 16k | — | $499 launch MSRP |
| GeForce RTX 5060 | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 4.3 tok/s3.5–5.2calibrated estimate ±20% | Q2_K | 8.0 / 8.0 GB + 8.4 GB RAM | Partial offload | up to 16k | — | $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 4.3 tok/s3.5–5.2calibrated estimate ±20% | Q2_K | 8.0 / 8.0 GB + 8.4 GB RAM | Partial offload | up to 16k | — | $429 street (as of 2026-08-09) |
| GeForce RTX 4060 Ti 8GB | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 4.1 tok/s3.3–5.0calibrated estimate ±20% | Q2_K | 8.0 / 8.0 GB + 8.4 GB RAM | Partial offload | up to 16k | — | $399 launch MSRP |
| GeForce RTX 4060 | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 4.1 tok/s3.3–4.9calibrated estimate ±20% | Q2_K | 8.0 / 8.0 GB + 8.4 GB RAM | Partial offload | up to 16k | — | $299 launch MSRP |
| GeForce RTX 4060 Laptop | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 4.1 tok/s3.3–4.9calibrated estimate ±20% | Q2_K | 8.0 / 8.0 GB + 8.4 GB RAM | Partial offload | up to 16k | — | — |
| GeForce RTX 4070 Laptop | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 4.1 tok/s3.3–4.9calibrated estimate ±20% | Q2_K | 8.0 / 8.0 GB + 8.4 GB RAM | Partial offload | up to 16k | — | — |
| GeForce RTX 3050 8GB | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 4.0 tok/s3.2–4.8calibrated estimate ±20% | Q2_K | 8.0 / 8.0 GB + 8.4 GB RAM | Partial offload | up to 16k | — | $249 launch MSRP |
| GeForce GTX 1080 Ti | Won't runTry IQ4_XS: Runs slowly | est. 3.5 tok/s2.5–4.6theoretical estimate ±30% | IQ4_XS | 11.0 / 11.0 GB + 10.6 GB RAM | Partial offload | up to 8k | — | $699 launch MSRP |
| GeForce RTX 3080 10GB | Won't runTry IQ4_XS: Runs slowly | est. 3.4 tok/s2.7–4.0calibrated estimate ±20% | IQ4_XS | 10.0 / 10.0 GB + 11.6 GB RAM | Partial offload | up to 8k | — | $699 launch MSRP |
| DDR5-6000 dual-channel CPU · 96 GB | Won't runTry Q2_K (heavy quality loss): Runs slowly | est. 3.1 tok/s2.5–3.8calibrated estimate ±20% | Q2_K | 15.3 GB RAM | CPU only | up to 8k | — | — |
| DDR5-5600 dual-channel CPU · 96 GB | Won't run | est. 2.0 tok/s1.6–2.4calibrated estimate ±20% | Q4_K_M | 22.5 GB RAM | CPU only | — |
| — |
| DDR4-3200 dual-channel CPU · 64 GB | Won't run | est. 1.1 tok/s0.9–1.4calibrated estimate ±20% | Q4_K_M | 22.5 GB RAM | CPU only | — |
| — |
Models with a thinking mode spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s). With thinking turned off, a model may do one grade better.
Cheapest GPUs that run it
- Runs greatGeForce RTX 4090$2,755 street (as of 2026-08-09), est. 31.3 tok/s (27.6–35.1, calibrated estimate ±12%).
- Runs wellGeForce RTX 3090$1,050 street (as of 2026-08-09), est. 29.1 tok/s (25.6–32.6, calibrated estimate ±12%).
Measured results for Nanbeige4.3 33B
No public measurements for this model yet.
Frequently asked questions
How much VRAM does Nanbeige4.3 33B need?
At Q4_K_M the file is 20.79 GB; with 8k context a graphics card needs about 22.4 GB (weights 20.11 GB, KV cache 1.7 GB, compute buffer 0.6 GB). The smallest tracked file (Q2_K (heavy quality loss)) needs about 14.6 GB. Part of the file stays off the graphics card: llama.cpp keeps the input embedding table in system RAM. A Mac counts the whole file, so it needs a little more.
What is the cheapest GPU that runs Nanbeige4.3 33B well?
Cheapest that runs it great: GeForce RTX 4090 at $2,755 (street price as of 2026-08-09), est. 31.3 tok/s (27.6–35.1, calibrated estimate ±12%). Cheaper and still Runs well: GeForce RTX 3090 at $1,050 (street price as of 2026-08-09), est. 29.1 tok/s (25.6–32.6, calibrated estimate ±12%).
Can Nanbeige4.3 33B run on an 8 GB, 16 GB or 24 GB GPU?
At Q4_K_M with 8k context: GeForce RTX 4060 — Won't run, est. 2.4 tok/s (2.0–2.9, calibrated estimate ±20%); GeForce RTX 5060 Ti 16GB — Runs slowly, est. 4.3 tok/s (3.5–5.2, calibrated estimate ±20%); GeForce RTX 3090 — Runs well, est. 29.1 tok/s (25.6–32.6, calibrated estimate ±12%).
Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.