Nanbeige4.2 3B hardware requirements
What is Nanbeige4.2 3B?
Nanbeige4.2 3B is a compact agentic model that Nanbeige LLM Lab released in July 2026. It is a looped transformer that reuses its layers to add capacity without adding parameters, with 3B non-embedding and 4B total parameters. Its card highlights general-agent, code-agent and reasoning tasks. Thinking is on by default and enable_thinking turns it off; the context reaches 262,144 tokens, and the Apache 2.0 license allows commercial use.
About the model
- Parameters
- 4.17B
- Attention
- Full attention
- Max context
- 262,144 tokens
- Released
- 2026-07-21
- Model card
- Nanbeige4.2 3B on Hugging Face
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| Q2_K | 1.85 GB | Heavy loss | Community GGUF · bartowski |
| IQ4_XS | 2.44 GB | Good balance | Community GGUF · bartowski |
| Q4_K_Mbaseline | 2.68 GB | Good balance | Community GGUF · bartowski |
| Q8_0 | 4.43 GB | Near-lossless | Community GGUF · bartowski |
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k | 256k |
|---|---|---|---|---|---|---|---|
| Q2_K | 3.0 | 3.7 | 5.3 | 8.4 | 14.6 | 27.0 | 51.8 |
| IQ4_XS | 3.4 | 4.2 | 5.8 | 8.9 | 15.1 | 27.5 | 52.3 |
| Q4_K_M | 3.7 | 4.4 | 6.0 | 9.1 | 15.3 | 27.7 | 52.5 |
| Q8_0 | 5.2 | 5.9 | 7.5 | 10.6 | 16.8 | 29.2 | 54.0 |
Which GPUs can run Nanbeige4.2 3B?
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
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. 204.8 tok/s143.3–266.2theoretical estimate ±30% | Q4_K_M | 5.0 / 32.0 GB | Full GPU | up to 128k | — | $4,200 street (as of 2026-08-09) |
| Radeon RX 7900 XTX | Runs great | est. 119.1 tok/s83.4–154.8theoretical estimate ±30% | Q4_K_M | 5.0 / 24.0 GB | Full GPU | up to 64k | — | $999 launch MSRP |
| GeForce RTX 3090 Ti | Runs great | est. 115.2 tok/s80.6–149.7theoretical estimate ±30% | Q4_K_M | 5.0 / 24.0 GB | Full GPU | up to 64k | — | $1,999 launch MSRP |
| GeForce RTX 4090 | Runs great | est. 115.2 tok/s80.6–149.7theoretical estimate ±30% | Q4_K_M | 5.0 / 24.0 GB | Full GPU | up to 64k | — | $2,755 street (as of 2026-08-09) |
| Apple M5 Ultra · 96 GB | Runs great | est. 114.3 tok/s80.0–148.5theoretical estimate ±30% | Q4_K_M | 4.7 / 67.2 GB | Unified memory | up to 64k | — | — |
| GeForce RTX 5080 | Runs great | est. 109.7 tok/s76.8–142.6theoretical estimate ±30% | Q4_K_M | 5.0 / 16.0 GB | Full GPU | up to 64k | — | $1,256 street (as of 2026-08-09) |
| GeForce RTX 3090 | Runs great | est. 106.9 tok/s74.9–139.0theoretical estimate ±30% | Q4_K_M | 5.0 / 24.0 GB | Full GPU | up to 64k | — | $1,050 street (as of 2026-08-09) |
| GeForce RTX 3080 12GB | Runs great | est. 104.2 tok/s72.9–135.5theoretical estimate ±30% | Q4_K_M | 5.0 / 12.0 GB | Full GPU | up to 32k | — | $799 launch MSRP |
| GeForce RTX 5070 Ti | Runs great | est. 102.4 tok/s71.7–133.1theoretical estimate ±30% | Q4_K_M | 5.0 / 16.0 GB | Full GPU | up to 64k | — | $949 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Runs great | est. 102.4 tok/s71.7–133.1theoretical estimate ±30% | Q4_K_M | 5.0 / 16.0 GB | Full GPU | up to 64k | — | — |
| GeForce RTX 5090 Laptop | Runs great | est. 102.4 tok/s71.7–133.1theoretical estimate ±30% | Q4_K_M | 5.0 / 24.0 GB | Full GPU | up to 64k | — | — |
| Radeon RX 7900 XT | Runs great | est. 99.2 tok/s69.5–129.0theoretical estimate ±30% | Q4_K_M | 5.0 / 20.0 GB | Full GPU | up to 64k | — | $899 launch MSRP |
| GeForce RTX 3080 10GB | Runs great | est. 86.8 tok/s60.8–112.9theoretical estimate ±30% | Q4_K_M | 5.0 / 10.0 GB | Full GPU | up to 32k | — | $699 launch MSRP |
| GeForce RTX 4080 Super | Runs great | est. 84.1 tok/s58.9–109.3theoretical estimate ±30% | Q4_K_M | 5.0 / 16.0 GB | Full GPU | up to 64k | — | $999 launch MSRP |
| GeForce RTX 4080 | Runs great | est. 81.9 tok/s57.3–106.5theoretical estimate ±30% | Q4_K_M | 5.0 / 16.0 GB | Full GPU | up to 64k | — | $1,199 launch MSRP |
| Radeon RX 9070 | Runs great | est. 80.0 tok/s56.0–104.0theoretical estimate ±30% | Q4_K_M | 5.0 / 16.0 GB | Full GPU | up to 32k | — | $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Runs great | est. 80.0 tok/s56.0–104.0theoretical estimate ±30% | Q4_K_M | 5.0 / 16.0 GB | Full GPU | up to 32k | — | $689 street (as of 2026-08-09) |
| Radeon RX 7800 XT | Runs great | est. 77.4 tok/s54.2–100.6theoretical estimate ±30% | Q4_K_M | 5.0 / 16.0 GB | Full GPU | up to 32k | — | $499 launch MSRP |
| GeForce RTX 4070 Ti Super | Runs great | est. 76.8 tok/s53.7–99.8theoretical estimate ±30% | Q4_K_M | 5.0 / 16.0 GB | Full GPU | up to 32k | — | $799 launch MSRP |
| GeForce RTX 5070 | Runs great | est. 76.8 tok/s53.7–99.8theoretical estimate ±30% | Q4_K_M | 5.0 / 12.0 GB | Full GPU | up to 32k | — | $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Runs great | est. 76.8 tok/s53.7–99.8theoretical estimate ±30% | Q4_K_M | 5.0 / 12.0 GB | Full GPU | up to 32k | — | — |
| Apple M3 Ultra · 96 GB | Runs great | est. 76.2 tok/s53.3–99.1theoretical estimate ±30% | Q4_K_M | 4.7 / 67.2 GB | Unified memory | up to 32k | — | — |
| Apple M5 Max (40-core GPU) · 48 GB | Runs great | est. 76.2 tok/s53.3–99.0theoretical estimate ±30% | Q4_K_M | 4.7 / 33.6 GB | Unified memory | up to 32k | — | — |
| Apple M2 Ultra · 64 GB | Runs great | est. 74.4 tok/s52.1–96.8theoretical estimate ±30% | Q4_K_M | 4.7 / 44.8 GB | Unified memory | up to 32k | — | — |
| GeForce RTX 2080 Ti | Runs great | est. 70.4 tok/s49.3–91.5theoretical estimate ±30% | Q4_K_M | 5.0 / 11.0 GB | Full GPU | up to 32k | — | $999 launch MSRP |
| Apple M4 Max (40-core GPU) · 48 GB | Runs great | est. 67.7 tok/s47.4–88.1theoretical estimate ±30% | Q4_K_M | 4.7 / 33.6 GB | Unified memory | up to 32k | — | — |
| GeForce RTX 4090 Laptop | Runs great | est. 65.8 tok/s46.1–85.6theoretical estimate ±30% | Q4_K_M | 5.0 / 16.0 GB | Full GPU | up to 32k | — | — |
| GeForce RTX 4070 | Runs great | est. 57.6 tok/s40.3–74.9theoretical estimate ±30% | Q4_K_M | 5.0 / 12.0 GB | Full GPU | up to 32k | — | $599 launch MSRP |
| GeForce RTX 4070 Super | Runs great | est. 57.6 tok/s40.3–74.9theoretical estimate ±30% | Q4_K_M | 5.0 / 12.0 GB | Full GPU | up to 32k | — | $599 launch MSRP |
| Apple M5 Max (32-core GPU) · 36 GB | Runs great | est. 57.1 tok/s39.9–74.2theoretical estimate ±30% | Q4_K_M | 4.7 / 25.2 GB | Unified memory | up to 32k | — | — |
| GeForce GTX 1080 Ti | Runs great | est. 55.3 tok/s38.7–71.9theoretical estimate ±30% | Q4_K_M | 5.0 / 11.0 GB | Full GPU | up to 32k | — | $699 launch MSRP |
| GeForce RTX 3070 | Runs great | est. 51.2 tok/s35.8–66.5theoretical estimate ±30% | Q4_K_M | 5.0 / 8.0 GB | Full GPU | up to 16k | — | $499 launch MSRP |
| GeForce RTX 5060 | Runs great | est. 51.2 tok/s35.8–66.5theoretical estimate ±30% | Q4_K_M | 5.0 / 8.0 GB | Full GPU | up to 16k | — | $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 16GB | Runs great | est. 51.2 tok/s35.8–66.5theoretical estimate ±30% | Q4_K_M | 5.0 / 16.0 GB | Full GPU | up to 16k | — | $569 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Runs great | est. 51.2 tok/s35.8–66.5theoretical estimate ±30% | Q4_K_M | 5.0 / 8.0 GB | Full GPU | up to 16k | — | $429 street (as of 2026-08-09) |
| Apple M4 Max (32-core GPU) · 36 GB | Runs great | est. 50.9 tok/s35.6–66.1theoretical estimate ±30% | Q4_K_M | 4.7 / 25.2 GB | Unified memory | up to 16k | — | — |
| GeForce RTX 4080 Laptop | Runs great | est. 49.4 tok/s34.6–64.2theoretical estimate ±30% | Q4_K_M | 5.0 / 12.0 GB | Full GPU | up to 16k | — | — |
| Intel Arc B580 | Runs great | est. 43.9 tok/s30.7–57.1theoretical estimate ±30% | Q4_K_M | 5.0 / 12.0 GB | Full GPU | up to 16k | — | $290 street (as of 2026-08-09) |
| GeForce RTX 3060 12GB | Runs great | est. 41.1 tok/s28.8–53.5theoretical estimate ±30% | Q4_K_M | 5.0 / 12.0 GB | Full GPU | up to 16k | — | $250 street (as of 2026-08-09) |
| Radeon RX 9060 XT 16GB | Runs great | est. 39.9 tok/s28.0–51.9theoretical estimate ±30% | Q4_K_M | 5.0 / 16.0 GB | Full GPU | up to 16k | — | $449 street (as of 2026-08-09) |
| Apple M5 Pro · 24 GB | Runs great | est. 38.1 tok/s26.7–49.5theoretical estimate ±30% | Q4_K_M | 4.7 / 16.8 GB | Unified memory | up to 16k | — | — |
| NVIDIA DGX Spark · 64 GB | Runs great | est. 34.8 tok/s24.3–45.2theoretical estimate ±30% | Q4_K_M | 4.7 / 48.2 GB | Unified memory | up to 8k | — | $3,999 launch MSRP (128 GB) |
| Ryzen AI Max+ 395 (Strix Halo) · 32 GB | Runs great | est. 34.3 tok/s24.0–44.5theoretical estimate ±30% | Q4_K_M | 4.7 / 22.4 GB | Unified memory | up to 8k | — | $1,999 launch MSRP (128 GB) |
| Apple M4 Pro · 24 GB | Runs great | est. 33.9 tok/s23.7–44.0theoretical estimate ±30% | Q4_K_M | 4.7 / 16.8 GB | Unified memory | up to 8k | — | — |
| GeForce RTX 4060 Ti 16GB | Runs great | est. 32.9 tok/s23.0–42.8theoretical estimate ±30% | Q4_K_M | 5.0 / 16.0 GB | Full GPU | up to 8k | — | $499 launch MSRP |
| GeForce RTX 4060 Ti 8GB | Runs great | est. 32.9 tok/s23.0–42.8theoretical estimate ±30% | Q4_K_M | 5.0 / 8.0 GB | Full GPU | up to 8k | — | $399 launch MSRP |
| GeForce RTX 4060 | Runs great | est. 31.1 tok/s21.8–40.4theoretical estimate ±30% | Q4_K_M | 5.0 / 8.0 GB | Full GPU | up to 8k | — | $299 launch MSRP |
| GeForce RTX 4060 Laptop | Runs well | est. 29.3 tok/s20.5–38.0theoretical estimate ±30% | Q4_K_M | 5.0 / 8.0 GB | Full GPU | up to 16k |
| — |
| GeForce RTX 4070 Laptop | Runs well | est. 29.3 tok/s20.5–38.0theoretical estimate ±30% | Q4_K_M | 5.0 / 8.0 GB | Full GPU | up to 16k |
| — |
| GeForce RTX 3050 8GB | Runs well | est. 25.6 tok/s17.9–33.3theoretical estimate ±30% | Q4_K_M | 5.0 / 8.0 GB | Full GPU | up to 16k |
| $249 launch MSRP |
| Apple M5 · 16 GB | Runs well | est. 19.1 tok/s13.3–24.8theoretical estimate ±30% | Q4_K_M | 4.7 / 11.2 GB | Unified memory | up to 16k | — | — |
| Apple M6 · 16 GB | Runs well | est. 19.1 tok/s13.3–24.8theoretical estimate ±30% | Q4_K_M | 4.7 / 11.2 GB | Unified memory | up to 16k | — | — |
| Apple M4 · 16 GB | Runs well | est. 14.9 tok/s10.4–19.4theoretical estimate ±30% | Q4_K_M | 4.7 / 11.2 GB | Unified memory | up to 8k | — | — |
| DDR5-6000 dual-channel CPU · 16 GB | Runs slowly | est. 7.8 tok/s5.5–10.2theoretical estimate ±30% | Q4_K_M | 4.2 GB RAM | CPU only | up to 32k | — | — |
| DDR5-5600 dual-channel CPU · 16 GB | Runs slowly | est. 7.3 tok/s5.1–9.5theoretical estimate ±30% | Q4_K_M | 4.2 GB RAM | CPU only | up to 32k | — | — |
| DDR4-3200 dual-channel CPU · 16 GB | Runs slowly | est. 4.2 tok/s2.9–5.4theoretical estimate ±30% | Q4_K_M | 4.2 GB RAM | CPU only | up to 16k | — | — |
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 3060 12GB$250 street (as of 2026-08-09), est. 41.1 tok/s (28.8–53.5, theoretical estimate ±30%).
Measured results for Nanbeige4.2 3B
No public measurements for this model yet.
Frequently asked questions
How much VRAM does Nanbeige4.2 3B need?
At Q4_K_M the file is 2.68 GB; with 8k context a graphics card needs about 4.4 GB (weights 2.39 GB, KV cache 1.5 GB, compute buffer 0.6 GB). The smallest tracked file (Q2_K (heavy quality loss)) needs about 3.7 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 Nanbeige4.2 3B well?
Cheapest that runs it great: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 41.1 tok/s (28.8–53.5, theoretical estimate ±30%).
Can Nanbeige4.2 3B run on an 8 GB, 16 GB or 24 GB GPU?
At Q4_K_M with 8k context: GeForce RTX 4060 — Runs great, est. 31.1 tok/s (21.8–40.4, theoretical estimate ±30%); GeForce RTX 5060 Ti 16GB — Runs great, est. 51.2 tok/s (35.8–66.5, theoretical estimate ±30%); GeForce RTX 3090 — Runs great, est. 106.9 tok/s (74.9–139.0, theoretical estimate ±30%).
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.