llmrun
XenovaQwen2ForCausalLM

Sweep Next Edit 1.5B — Hardware Requirements & GPU Compatibility

ChatCode

Sweep Next Edit 1.5B is a 1.4B-parameter open language model from Xenova. It supports a context window of up to 32,768 tokens. At Q4_K_M it needs about 1.19 GB of VRAM — see which GPUs and Macs can run it below.

1.4B params · dense33K contextApache 2.067.0K downloads159 quant downloads
S

Runs great on a 24 GB GPU

Runs from8 GB Q4_K_M · 32KBest on24 GB Q4_K_M · ~551 tok/s · 32KMacs from8 GB Q4_K_M · ~60 tok/s

Apache 2.0

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Sweep Next Edit 1.5B

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
one command · needs vLLM installed
$vllm serve Xenova/sweep-next-edit-1.5B --max-model-len 16384

vLLM repo with its own quantisation

Download: Weights on Hugging Face

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Runs on RTX 3060 12GB (10 GB headroom) · Q4_K_M

Generation speed
~197 tok/s
generation speed
Cost per 1M output tokens
$0.089
per 1M output tokens

How Much VRAM Does Sweep Next Edit 1.5B Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
0.9 GB1.8 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 32K context · ~697 tok/s
1.0 GB1.9 GB3-bit medium — 3-bit medium quantizationFits: 32K context · ~636 tok/s
1.2 GB2.1 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 32K context · ~551 tok/s
1.3 GB2.2 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 32K context · ~489 tok/s
1.5 GB2.4 GB6-bit, very good — 6-bit quantization, very good qualityFits: 32K context · ~437 tok/s
1.7 GB2.6 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 32K context · ~377 tok/s
3.1 GB4 GB16-bit · bfloat — Brain floating point 16 — preferred for trainingFits: 32K context · ~211 tok/s
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

1.6GBat 16K context

Weights
0.8 GB
KV cache
0.5 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 22.4 GB free · ~551 tok/s

≥50 tok/s needs ≥91 GB/s · RTX 5090 ~979, M5 Ultra ~722

Which Hardware Can Run Sweep Next Edit 1.5B?

Q4_K_M · 1.2 GB

Sweep Next Edit 1.5B (Q4_K_M) requires 1.2 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 33K context window can add up to 0.9 GB, bringing total usage to 2.1 GB. 114 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 185 devices with unified memory can run Sweep Next Edit 1.5B, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060Q4_K_M · 1.6 GB · ~149 tok/s · 32K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 1.6 GB · ~197 tok/s · 32K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 1.6 GB · ~245 tok/s · 32K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 1.6 GB · ~551 tok/s · 32K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 1.6 GB · ~71 tok/s · 32KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 1.6 GB · ~321 tok/s · 32KMacs →

Alternatives to Sweep Next Edit 1.5B

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
MiniCPM V 4.6 ThinkingOpenBMB—1.5 GB~580same size
Inkling Small DSpark PreviewRadixArk—1.5 GB~555same size
OLMo 2 0425 1B InstructAllen AI—1.7 GB~449same size
Granite 3.0 1B A400m InstructIBM—1.3 GB~524same size
MobileLLaMA 1.4B Chatmtgv—1.5 GB~426same size
Phi 1 5Microsoft—0.9 GB~697same size

Specifications

Publisher
Xenova
Parameters
1.4B
Architecture
Qwen2ForCausalLM
Context Length
32,768 tokens
Vocabulary Size
43,839
Release Date
2026-01-23
License
Apache 2.0

Frequently Asked Questions

How much VRAM does Sweep Next Edit 1.5B need?

Sweep Next Edit 1.5B requires 1.2 GB of VRAM at Q4_K_M, or 3.1 GB at BF16. Full 33K context adds up to 0.9 GB (2.1 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 1.4B × 4.8 bits ÷ 8 = 0.8 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.

KV Cache + Overhead ≈ 1.3 GB (at full 33K context)

VRAM usage by quantization

1.2 GB
2.1 GB

Learn more about VRAM estimation →

What's the best quantization for Sweep Next Edit 1.5B?

For Sweep Next Edit 1.5B, Q4_K_M (1.2 GB) offers the best balance of quality and VRAM usage. Q5_K_M (1.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.9 GB.

VRAM requirement by quantization

Q2_K
0.9 GB
Q4_K_M ★
1.2 GB
Q5_K_M
1.3 GB
Q6_K
1.5 GB
Q8_0
1.7 GB
BF16
3.1 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Sweep Next Edit 1.5B on a Mac?

Yes — MacBook Air 13" M3 (8 GB) and 158 other Macs can run Sweep Next Edit 1.5B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.2 GB of usable unified memory (RAM minus macOS overhead).

Can I run Sweep Next Edit 1.5B locally?

Yes — Sweep Next Edit 1.5B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Sweep Next Edit 1.5B?

At Q4_K_M, Sweep Next Edit 1.5B can reach ~4034 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~551 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 ÷ 1.19 × 0.65 = ~4370 tok/s

Estimated speed at Q4_K_M (1.2 GB)

~4370 tok/s
~551 tok/s
~4370 tok/s
~4034 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Sweep Next Edit 1.5B?

At Q4_K_M, the download is about 0.83 GB. The full-precision BF16 version is 2.76 GB. The smallest option (Q2_K) is 0.59 GB.

Which GPUs can run Sweep Next Edit 1.5B?

114 consumer GPUs can run Sweep Next Edit 1.5B 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 Sweep Next Edit 1.5B?

185 devices with unified memory can run Sweep Next Edit 1.5B at Q4_K_M (1.2 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.