RedPajama INCITE 7B Base — Hardware Requirements & GPU Compatibility
Chat
RedPajama-INCITE-7B-Base is Together Computer's open base pretrained language model, not instruction-tuned, with roughly 6.9 billion parameters trained on the RedPajama-Data-1T dataset, an open reproduction of the corpus used to train Meta's original LLaMA. It was developed with a consortium including Ontocord.ai, ETH DS3Lab, Stanford CRFM and Hazy Research, and LAION, using compute awarded through the 2023 INCITE program. Instruction-tuned and chat variants, RedPajama-INCITE-7B-Instruct and RedPajama-INCITE-7B-Chat, were released alongside it. At under 7 billion parameters it runs on a single consumer GPU. Context length is 2,048 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use. It was published in May 2023, as one of the first fully open, commercially usable base models trained on openly licensed data.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 2K)Best on 24 GB (Q4_K_M · ~142 tok/s · 2K)Macs from 8 GB (Q3_K_M · ~19 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run RedPajama INCITE 7B Base
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve togethercomputer/RedPajama-INCITE-7B-Base --max-model-len 2048vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3080 Ti (12 GB) (7 GB headroom) · Q4_K_M
- Generation speed
- ~128 tok/s
- generation speed
- Cost per 1M output tokens
- $0.26
- per 1M output tokens
How Much VRAM Does RedPajama INCITE 7B Base Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 3.3 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 2K context · ~200 tok/s | |
| 3.8 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 2K context · ~175 tok/s | |
| 4.6 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 2K context · ~142 tok/s | |
| 5.5 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 2K context · ~119 tok/s | |
| 6.3 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 2K context · ~103 tok/s | |
| 7.7 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 2K context · ~85 tok/s | |
| 15.4 GB | — | 16-bit · full — Full half-precision — baseline for inference | Fits: 2K context · ~43 tok/s |
Selected Q4_K_M
4-bit medium quantization4.6GBat 2K context
- Weights
- 4.0 GB
- KV cache
- 0.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 19.4 GB free · ~142 tok/s
≥50 tok/s needs ≥355 GB/s · RTX 5090 ~252, RTX 3090 Ti ~142
Which Hardware Can Run RedPajama INCITE 7B Base?
Q4_K_M · 4.6 GBRedPajama INCITE 7B Base (Q4_K_M) requires 4.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 151 devices with unified memory can run RedPajama INCITE 7B Base, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 3.4 GB free · up to 2K ctx
16 GPUs · 2 device families
RTX 3080~107Simulate output on RTX 3080RTX 2080 Ti~87Simulate output on RTX 2080 TiRTX 3070 Ti~86Simulate output on RTX 3070 TiOrin Nano~14Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~10Simulate output on iPhone 1720 GB
fits · 15.4 GB free · up to 2K ctx
1 GPU
RX 7900 XT~104Simulate output on RX 7900 XT32–40 GB
fits · 27.4 GB free · up to 2K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~252Simulate output on RTX 5090M5 Max36 GB~70Simulate output on Mac Studio M5 Max (36 GB)M532 GB~23Simulate output on MacBook Air 13" M5 (32 GB)Orin~29Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~19Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
How good is RedPajama INCITE 7B Base?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
The 6 boards that weigh most in the llmrun Score, of 7 with a result for this model; badges show who ran the test.
- MMLU
Epoch AI · May 2023Lab-reported
Lab-reported26.3%
#81/85 open
- HellaSwag
Epoch AI · May 2023Lab-reported
Lab-reported70.3%
#35/47 open
- ARC Challenge
Epoch AI · May 2023Lab-reported
Lab-reported39.1%
#42/56 open
- WinoGrande
Epoch AI · May 2023Lab-reported
Lab-reported63.8%
#39/51 open
- BoolQ
Epoch AI · May 2023Lab-reported
Lab-reported69.3%
#27/38 open
- OpenBookQA
Epoch AI · May 2023Lab-reported
Lab-reported40.0%
#17/26 open
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Olmo 3 7B InstructAllen AI | — | 8.4 GB | ~114 | same size |
| Mistral 7B Instruct v0.3Mistral AI | — | 6.8 GB | ~133 | same size |
| Phi 3 Small 8k InstructMicrosoft | — | 16.2 GB | ~43 | same size |
| CodeQwen1.5 7BAlibaba | — | 5.7 GB | ~137 | same size |
| Llava 1.5 7B HFllava-hf | — | 5 GB | ~141 | same size |
| Baichuan2 7B Basebaichuan-inc | — | 5 GB | ~142 | same size |
Specifications
- Publisher
- togethercomputer
- Parameters
- 7B
- Architecture
- GPTNeoXForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 50,432
- Release Date
- 2023-05-04
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does RedPajama INCITE 7B Base need?
RedPajama INCITE 7B Base requires 4.6 GB of VRAM at Q4_K_M, or 15.4 GB at FP16.
VRAM = Weights + KV Cache + Overhead
Weights = 7B × 4.8 bits ÷ 8 = 4.2 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
VRAM usage by quantization
What's the best quantization for RedPajama INCITE 7B Base?
For RedPajama INCITE 7B Base, Q4_K_M (4.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (5.5 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 3.3 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run RedPajama INCITE 7B Base on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run RedPajama INCITE 7B Base, the smallest at Q3_K_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 4.6 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M2 Pro (16 GB).
Can I run RedPajama INCITE 7B Base locally?
Yes — RedPajama INCITE 7B Base can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is RedPajama INCITE 7B Base?
At Q4_K_M, RedPajama INCITE 7B Base can reach ~1039 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~142 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 4.62 × 0.65 = ~1126 tok/s
Estimated speed at Q4_K_M (4.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of RedPajama INCITE 7B Base?
At Q4_K_M, the download is about 4.20 GB. The full-precision FP16 version is 14.00 GB. The smallest option (Q2_K) is 2.98 GB.
Which GPUs can run RedPajama INCITE 7B Base?
52 consumer GPUs can run RedPajama INCITE 7B Base at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
Which devices can run RedPajama INCITE 7B Base?
151 devices with unified memory can run RedPajama INCITE 7B Base at Q4_K_M (4.6 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.