Amber — Hardware Requirements & GPU Compatibility
Chat
Amber is a 6.7 billion parameter model from LLM360, an initiative dedicated to full transparency in large language model training. Every aspect of Amber's creation has been publicly documented and released, including the complete training data, all intermediate checkpoints, training code, and evaluation results. This level of openness makes Amber uniquely valuable for researchers studying training dynamics, data influence, and model behavior at scale. For local deployment, it offers solid general-purpose text generation at a size that fits comfortably on mid-range consumer GPUs, though users primarily seeking chat performance may prefer models specifically tuned for instruction following.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 2K)Best on 24 GB (Q4_K_M · ~121 tok/s · 2K)Macs from 8 GB (IQ3_M · ~16 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Amber
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
ollama run hf.co/mradermacher/Amber-i1-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 18.6 GB free · 2K context
Download: Amber.i1-Q4_K_M.gguf4.08 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3080 Ti (12 GB) (6 GB headroom) · Q4_K_M
- Generation speed
- ~109 tok/s
- generation speed
- Cost per 1M output tokens
- $0.31
- per 1M output tokens
How Much VRAM Does Amber Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 4.2 GB | — | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 2K context · ~155 tok/s | |
| 4.3 GB | — | 3-bit small — 3-bit small quantization | Fits: 2K context · ~152 tok/s | |
| 4.7 GB | — | 3-bit medium — 3-bit medium quantization | Fits: 2K context · ~141 tok/s | |
| 4.7 GB | — | 4-bit · legacy — 4-bit legacy quantization | Fits: 2K context · ~138 tok/s | |
| 5.4 GB | — | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 2K context · ~121 tok/s | |
| 6.2 GB | — | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 2K context · ~106 tok/s | |
| 6.9 GB | — | 6-bit, very good — 6-bit quantization, very good quality | Fits: 2K context · ~95 tok/s | |
| 8.1 GB | — | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 2K context · ~81 tok/s |
Selected Q4_K_M
4-bit medium quantization5.4GBat 2K context
- Weights
- 4.1 GB
- KV cache
- 1.1 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 18.6 GB free · ~121 tok/s
≥50 tok/s needs ≥417 GB/s · RTX 5090 ~215, RTX 3090 Ti ~121
Which Hardware Can Run Amber?
Q4_K_M · 5.4 GBAmber (Q4_K_M) requires 5.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti. 151 devices with unified memory can run Amber, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), NVIDIA Jetson Orin Nano 8GB (Super).
≤ 11 GB
≤ 11 GB tier →fits · 2.6 GB free · up to 2K ctx
16 GPUs · 1 device family
RTX 3080~91Simulate output on RTX 3080RTX 2080 Ti~74Simulate output on RTX 2080 TiRTX 3070 Ti~73Simulate output on RTX 3070 TiOrin Nano~12Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)20 GB
fits · 14.6 GB free · up to 2K ctx
1 GPU
RX 7900 XT~89Simulate output on RX 7900 XT32–40 GB
fits · 26.6 GB free · up to 2K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~215Simulate output on RTX 5090M5 Max36 GB~59Simulate output on Mac Studio M5 Max (36 GB)M532 GB~20Simulate output on MacBook Air 13" M5 (32 GB)Orin~25Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~16Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Mistral 7B Instruct v0.3Mistral AI | — | 6.8 GB | ~133 | same size |
| CodeQwen1.5 7BAlibaba | — | 5.7 GB | ~137 | same size |
| Llava 1.5 7B HFllava-hf | — | 5 GB | ~141 | same size |
| Chatglm3 6BZ.ai | — | 5.2 GB | ~159 | same size |
| Baichuan2 7B Basebaichuan-inc | — | 5 GB | ~142 | same size |
| Internlm 7BInternLM | — | 15.4 GB | ~43 | same size |
Specifications
- Publisher
- LLM360
- Parameters
- 6.7B
- Architecture
- LlamaForCausalLM
- Context Length
- 2,048 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2023-12-07
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Amber need?
Amber requires 5.4 GB of VRAM at Q4_K_M, or 14.8 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 6.7B × 4.8 bits ÷ 8 = 4 GB
KV Cache + Overhead ≈ 1.4 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 Amber?
For Amber, Q4_K_M (5.4 GB) offers the best balance of quality and VRAM usage. Q5_0 (5.6 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 3.2 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Amber on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Amber, the smallest at IQ3_M. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 5.4 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M2 Pro (16 GB).
Can I run Amber locally?
Yes — Amber can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Amber?
At Q4_K_M, Amber can reach ~886 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~121 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 ÷ 5.42 × 0.65 = ~959 tok/s
Estimated speed at Q4_K_M (5.4 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Amber?
At Q4_K_M, the download is about 4.04 GB. The full-precision BF16 version is 13.48 GB. The smallest option (IQ2_XXS) is 1.85 GB.
Which GPUs can run Amber?
52 consumer GPUs can run Amber at Q4_K_M. Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 40 GPUs have plenty of headroom for comfortable inference.
Which devices can run Amber?
151 devices with unified memory can run Amber at Q4_K_M (5.4 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.