ReaderLM v2 — Hardware Requirements & GPU Compatibility
Chat
ReaderLM v2 is a 1.5B-parameter open language model from jinaai. It supports a context window of up to 512,768 tokens. At Q4_K_M it needs about 1.28 GB of VRAM — see which GPUs and Macs can run it below.
361.3K downloads
792 likesSpecifications
- Publisher
- jinaai
- Parameters
- 1.5B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 512,768 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2025-03-04
- License
- CC BY-NC 4.0
Get Started
HuggingFace
How Much VRAM Does ReaderLM v2 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 1.0 GB | 15.7 GB | 0.66 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 1.0 GB | 15.7 GB | 0.68 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 1.1 GB | 15.8 GB | 0.75 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 1.3 GB | 15.9 GB | 0.93 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 1.5 GB | 16.1 GB | 1.10 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 1.6 GB | 16.3 GB | 1.27 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 1.9 GB | 16.6 GB | 1.54 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run ReaderLM v2?
Q4_K_M · 1.3 GBReaderLM v2 (Q4_K_M) requires 1.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ GB is recommended. Using the full 513K context window can add up to 14.7 GB, bringing total usage to 15.9 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run ReaderLM v2?
Q4_K_M · 1.3 GB33 devices with unified memory can run ReaderLM v2, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does ReaderLM v2 need?
ReaderLM v2 requires 1.3 GB of VRAM at Q4_K_M, or 1.9 GB at Q8_0. Full 513K context adds up to 14.7 GB (15.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.5B × 4.8 bits ÷ 8 = 0.9 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 15 GB (at full 513K context)
VRAM usage by quantization
Q4_K_M1.3 GBQ4_K_M + full context15.9 GB- What's the best quantization for ReaderLM v2?
For ReaderLM v2, Q4_K_M (1.3 GB) offers the best balance of quality and VRAM usage. Q5_K_S (1.4 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.0 GB.
VRAM requirement by quantization
Q2_K1.0 GBQ3_K_L1.1 GBQ4_K_S1.2 GBQ4_K_M ★1.3 GBQ5_K_M1.5 GBQ8_01.9 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run ReaderLM v2 on a Mac?
ReaderLM v2 requires at least 1.0 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run ReaderLM v2 locally?
Yes — ReaderLM v2 can run locally on consumer hardware. At Q4_K_M quantization it needs 1.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is ReaderLM v2?
At Q4_K_M, ReaderLM v2 can reach ~2277 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~512 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 1.3 × 0.55 = ~2277 tok/s
Estimated speed at Q4_K_M (1.3 GB)
~2277 tok/s~512 tok/s~1702 tok/s~1408 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of ReaderLM v2?
At Q4_K_M, the download is about 0.93 GB. The full-precision Q8_0 version is 1.54 GB. The smallest option (Q2_K) is 0.66 GB.
- Which GPUs can run ReaderLM v2?
35 consumer GPUs can run ReaderLM v2 at Q4_K_M (1.3 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run ReaderLM v2?
33 devices with unified memory can run ReaderLM v2 at Q4_K_M (1.3 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.