Small Qwen2ForCausalLM 2.5 — Hardware Requirements & GPU Compatibility
ChatFunctions
Small Qwen2ForCausalLM 2.5 is a 39M-parameter open language model from trl-internal-testing in the Qwen 2 family. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 0.32 GB of VRAM — see which GPUs and Macs can run it below.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 32K)Best on 24 GB (Q4_K_M · ~2048 tok/s · 32K)Macs from 8 GB (Q4_K_M · ~224 tok/s)
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Small Qwen2ForCausalLM 2.5
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/small-Qwen2ForCausalLM-2.5-i1-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 23.7 GB free · 16K context
Download: small-Qwen2ForCausalLM-2.5.i1-Q4_K_M.gguf0.04 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 (10 GB) (9 GB headroom) · Q4_K_M
- Generation speed
- ~1544 tok/s
- generation speed
- Cost per 1M output tokens
- $0.020
- per 1M output tokens
How Much VRAM Does Small Qwen2ForCausalLM 2.5 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.3 GB | 0.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 32K context · ~2048 tok/s | |
| 0.3 GB | 0.3 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 32K context · ~2048 tok/s | |
| 0.3 GB | 0.3 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 32K context · ~2048 tok/s | |
| 0.3 GB | 0.3 GB | 3-bit small — 3-bit small quantization | Fits: 32K context · ~2048 tok/s | |
| 0.3 GB | 0.3 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 32K context · ~2048 tok/s | |
| 0.3 GB | 0.4 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 32K context · ~1986 tok/s | |
| 0.3 GB | 0.4 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 32K context · ~1986 tok/s | |
| 0.3 GB | 0.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 32K context · ~1927 tok/s |
Selected Q4_K_M
4-bit medium quantization0.3GBat 16K context
- Weights
- 0.1 GB
- KV cache
- 0.0 GB
- Overhead
- 0.3 GB
Which Hardware Can Run Small Qwen2ForCausalLM 2.5?
Q4_K_M · 0.3 GBSmall Qwen2ForCausalLM 2.5 (Q4_K_M) requires 0.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 1+ GB is recommended. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 185 devices with unified memory can run Small Qwen2ForCausalLM 2.5, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB).
≤ 11 GB
≤ 11 GB tier →fits · 3.7 GB free · up to 32K ctx
68 GPUs · 1 Mac class · 3 device families
RTX 3080~1544Simulate output on RTX 3080RTX 2080 Ti~1251Simulate output on RTX 2080 TiRTX 3070 Ti~1236Simulate output on RTX 3070 TiM3*8 GB~224Simulate output on iMac 24" M3 (8 GB)Orin Nano~207Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~149Simulate output on iPhone 1720 GB
fits · 19.7 GB free · up to 32K ctx
1 GPU
RX 7900 XT~1500Simulate output on RX 7900 XT32–40 GB
fits · 31.7 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 9 device families
RTX 5090~3640Simulate output on RTX 5090M5 Max*36 GB~1006Simulate output on Mac Studio M5 Max (36 GB)M632 GB~372Simulate output on iMac 24" M6 (32 GB)RTX Spark N1X~611Simulate output on NVIDIA RTX Spark N1X Laptop (32 GB)Orin~416Simulate output on NVIDIA Jetson AGX Orin 32GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Small Qwen2ForCausalLM 2.5
Qwen 2 family · 14 models →Similar models
2| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Stories15M MOEggml-org | — | 0.3 GB | ~1360 | same size |
| Gpt2 Minierwanf | — | 0 GB | ~21840 | same size |
Specifications
- Publisher
- trl-internal-testing
- Family
- Qwen 2
- Parameters
- 39M
- Architecture
- Qwen2ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 152,064
- Release Date
- 2025-01-12
Frequently Asked Questions
How much VRAM does Small Qwen2ForCausalLM 2.5 need?
Small Qwen2ForCausalLM 2.5 requires 0.3 GB of VRAM at Q4_K_M, or 0.4 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 39M × 4.8 bits ÷ 8 = 0 GB
KV Cache + Overhead ≈ 0.3 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.
KV Cache + Overhead ≈ 0.3 GB (at full 33K context)
VRAM usage by quantization
What's the best quantization for Small Qwen2ForCausalLM 2.5?
For Small Qwen2ForCausalLM 2.5, Q4_K_M (0.3 GB) offers the best balance of quality and VRAM usage. Q6_K (0.3 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 0.3 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Small Qwen2ForCausalLM 2.5 on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 158 other Macs can run Small Qwen2ForCausalLM 2.5. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 0.3 GB of usable unified memory (RAM minus macOS overhead).
Can I run Small Qwen2ForCausalLM 2.5 locally?
Yes — Small Qwen2ForCausalLM 2.5 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Small Qwen2ForCausalLM 2.5?
At Q4_K_M, Small Qwen2ForCausalLM 2.5 can reach ~15000 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~2048 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 ÷ 0.32 × 0.65 = ~16250 tok/s
Estimated speed at Q4_K_M (0.3 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Small Qwen2ForCausalLM 2.5?
At Q4_K_M, the download is about 0.02 GB. The full-precision BF16 version is 0.08 GB. The smallest option (IQ2_XXS) is 0.01 GB.
Which GPUs can run Small Qwen2ForCausalLM 2.5?
114 consumer GPUs can run Small Qwen2ForCausalLM 2.5 at Q4_K_M. Top options include AMD Radeon RX 5600 XT, AMD Radeon RX 5700 XT, AMD Radeon RX 580 8GB. 114 GPUs have plenty of headroom for comfortable inference.
Which devices can run Small Qwen2ForCausalLM 2.5?
185 devices with unified memory can run Small Qwen2ForCausalLM 2.5 at Q4_K_M (0.3 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.